INDEX

Explanations

references to news agencies or press releases

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

pson

-0.15

cÃ©

-0.15

mar

-0.15

 Loft

-0.14

aily

-0.14

illage

-0.14

ra

-0.14

apter

-0.14

ret

-0.13

lem

-0.13

POSITIVE LOGITS

 Picker

0.17

ÐĲÑĢÑħÑĸÐ²

0.15

plr

0.15

eyen

0.15

Mol

0.14

EATURE

0.14

SENS

0.13

utar

0.13

iddi

0.13

Ð³Ð°Ð»Ñĸ

0.13

Activations Density 0.003%

references to news agencies or press releases

No Comments

No Known Activations