INDEX

Explanations

specific nouns and proper names related to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Maul

-0.17

heet

-0.15

-0.14

Bak

-0.14

aliz

-0.14

 Este

-0.13

uiltin

-0.13

POSITIVE LOGITS

 promin

0.15

gor

0.15

ubar

0.15

CRET

0.14

nob

0.14

 ance

0.14

tons

0.14

åİħ

0.14

à¸´à¸Ī

0.14

_facebook

0.14

Activations Density 0.021%

specific nouns and proper names related to various contexts

No Comments

No Known Activations