INDEX

Explanations

informational content about price changes and templates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

umont

-0.14

sto

-0.14

opi

-0.13

nection

-0.13

unker

-0.13

Ã¤hr

-0.13

 Convention

-0.13

Ð½Ð¸ÑĨÑĮ

-0.13

dor

-0.13

isObject

-0.13

POSITIVE LOGITS

etc

0.19

etc

0.15

VERTEX

0.14

å»Ĭ

0.14

@foreach

0.13

 çŃī

0.13

 ruku

0.13

endregion

0.13

çłĤ

0.13

.bc

0.13

Activations Density 0.036%

informational content about price changes and templates

No Comments

No Known Activations