INDEX

Explanations

references to incomplete tasks or 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

undi

-0.15

pas

-0.15

adolu

-0.15

wer

-0.14

ierz

-0.14

neas

-0.14

ksi

-0.14

 trá»¥c

-0.14

ix

-0.13

 Cove

-0.13

POSITIVE LOGITS

ohl

0.16

prung

0.14

Gam

0.14

Ø¡

0.14

[:]

0.14

nerg

0.14

owell

0.14

 Shak

0.14

emodel

0.13

SharedPtr

0.13

Activations Density 0.007%

references to incomplete tasks or comments in code

No Comments

No Known Activations