INDEX

Explanations

block comments in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ÑĢÐ¸Ð½

-0.16

 gÃ¬

-0.16

ãĥ¼ãĥĵ

-0.15

bul

-0.14

eka

-0.14

kit

-0.14

ulton

-0.14

ora

-0.14

/w

-0.14

eder

-0.14

POSITIVE LOGITS

ARGS

0.16

Ļ¨

0.15

lift

0.14

 Bever

0.14

ustralia

0.14

feit

0.13

/testing

0.13

arra

0.13

ABEL

0.13

ãģĦ

0.13

Activations Density 0.015%

block comments in code

No Comments

No Known Activations