INDEX

Explanations

questions or clauses related to inclusion, conditions, and descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

èĢĮ

-0.16

 Kill

-0.15

ly

-0.15

tti

-0.15

xy

-0.14

isko

-0.14

ney

-0.14

reo

-0.14

 Mein

-0.14

 which

-0.13

POSITIVE LOGITS

AUTHORIZED

0.15

 dobr

0.15

ãĥ³ãĥĲ

0.15

aghan

0.14

/how

0.14

'il

0.14

Ð¾Ð»Ð¾ÑĤ

0.14

erville

0.13

 ç¢

0.13

ynes

0.13

Activations Density 0.074%

questions or clauses related to inclusion, conditions, and descriptions

No Comments

No Known Activations