INDEX

Explanations

negative actions and attitudes that hinder interpersonal relationships and community engagement

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Leban

-0.17

ze

-0.16

ecome

-0.16

rror

-0.15

bee

-0.14

hev

-0.14

dana

-0.14

oleon

-0.14

imson

-0.14

ÎŃÏģ

-0.14

POSITIVE LOGITS

any

0.16

let

0.16

 McMahon

0.15

ãģĶ

0.14

 McDonald

0.14

tap

0.14

 anything

0.14

tap

0.14

 even

0.14

 Room

0.14

Activations Density 0.372%

negative actions and attitudes that hinder interpersonal relationships and community engagement

No Comments

No Known Activations