INDEX

Explanations

references to notable individuals and their statements or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

æľŁå¾ħ

-0.16

éĺħè¯»æ¬¡æķ°

-0.16

ocab

-0.15

@student

-0.14

åľ¨çº¿éĺħè¯»

-0.14

-mark

-0.13

VisualStyle

-0.13

 ì²¨ë¶Ģ

-0.13

ÃŃsto

-0.13

 Ã¼zer

-0.13

POSITIVE LOGITS

 talk

0.35

 talking

0.31

 speak

0.31

 talks

0.31

 speaking

0.31

 address

0.30

 addresses

0.30

-talk

0.28

 speaks

0.28

 Address

0.28

Activations Density 0.057%

references to notable individuals and their statements or actions

No Comments

No Known Activations