INDEX

Explanations

phrases that indicate functions, roles, or processes within 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

åĲĦç§į

-0.14

UDO

-0.14

aload

-0.14

misc

-0.14

 å¾ĴæŃ©

-0.14

 Multiple

-0.13

scribed

-0.13

Î¬Î½Î¹

-0.13

 Various

-0.13

-ending

-0.13

POSITIVE LOGITS

 most

0.58

 majority

0.57

 many

0.54

 some

0.49

many

0.45

 Ð±Ð¾Ð»ÑĮÑĪÐ¸Ð½

0.45

 meisten

0.45

most

0.43

 Majority

0.40

 Many

0.40

Activations Density 0.002%

phrases that indicate functions, roles, or processes within various contexts

No Comments

No Known Activations