INDEX

Explanations

code-related components and expressions, specifically focusing on functions and event handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

aight

-0.16

jal

-0.14

imits

-0.14

igh

-0.13

cÃ©

-0.13

 Jacobs

-0.13

ãĤ¤ãĤ¯

-0.13

 Pulitzer

-0.13

okino

-0.13

 sire

-0.13

POSITIVE LOGITS

[,]

0.14

cf

0.14

Æ°á»£

0.14

ãĤ¯ãĥĪ

0.14

 hoÃ¡

0.14

 restores

0.13

Ńå·ŀ

0.13

è¡Ŀ

0.13

xcf

0.13

Activations Density 0.120%

code-related components and expressions, specifically focusing on functions and event handling

No Comments

No Known Activations