INDEX

Explanations

code-related keywords and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

bsites

-0.16

FindObject

-0.15

izzes

-0.15

utterstock

-0.15

cntl

-0.15

MenuStrip

-0.15

umbn

-0.14

EY

-0.14

utsch

-0.14

lessly

-0.14

POSITIVE LOGITS

 vess

0.17

 Herr

0.16

ê°Ĳ

0.15

0.14

 opening

0.14

bias

0.14

REC

0.14

ines

0.14

 ActionController

0.13

taj

0.13

Activations Density 0.103%

code-related keywords and function definitions

No Comments

No Known Activations