INDEX

Explanations

return statements 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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

omik

-0.19

rana

-0.16

ches

-0.15

oa

-0.15

entials

-0.15

auga

-0.14

anela

-0.14

Ø§Ø´

-0.13

ohana

-0.13

inx

-0.13

POSITIVE LOGITS

0.16

olina

0.16

 Barton

0.14

ow

0.14

en

0.14

ãĥ³ãĥĸ

0.14

roups

0.13

##_

0.13

arth

0.13

Hob

0.13

Activations Density 0.049%

return statements in code

No Comments

No Known Activations