INDEX

Explanations

code-related terminology and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

urch

-0.17

pter

-0.15

-0.14

ora

-0.14

stdin

-0.14

ulous

-0.14

rib

-0.13

ibu

-0.13

POSITIVE LOGITS

 return

0.69

return

0.63

 Return

0.58

 RETURN

0.55

è¿ĶåĽŀ

0.55

 returning

0.54

-return

0.54

 returns

0.54

Return

0.53

 returned

0.53

Activations Density 0.510%

code-related terminology and functions

No Comments

No Known Activations