INDEX

Explanations

phrases that express generalizations or overarching themes

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

ed

-0.20

gener

-0.20

ä¸ĢèĪ¬

-0.18

 gÃ©nÃ©

-0.18

 ä¸ĢèĪ¬

-0.16

 General

-0.16

General

-0.16

 gÃ©nÃ©ral

-0.15

uien

-0.15

 generally

-0.15

POSITIVE LOGITS

ised

0.44

-purpose

0.44

izations

0.42

izable

0.42

ization

0.38

isations

0.37

ities

0.36

izing

0.35

iz

0.33

izes

0.31

Activations Density 0.036%

phrases that express generalizations or overarching themes

No Comments

No Known Activations