INDEX

Explanations

words associated with appreciation and commendation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Lists

-0.18

ÅĽÄĩ

-0.17

ueur

-0.17

ureau

-0.16

 Teams

-0.16

atorio

-0.16

eer

-0.15

urette

-0.15

levance

-0.15

Lists

-0.14

POSITIVE LOGITS

ities

0.33

ä»¬

0.33

backs

0.28

ippets

0.26

ies

0.26

uels

0.25

ences

0.25

ties

0.25

ths

0.24

lates

0.24

Activations Density 0.091%

words associated with appreciation and commendation

No Comments

No Known Activations