INDEX

Explanations

instances of reported speech or statements in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

avier

-0.17

Alv

-0.15

oes

-0.14

 personally

-0.14

Ð¾ÑĤÑĮ

-0.14

thur

-0.14

asz

-0.14

 opposite

-0.14

avy

-0.14

existent

-0.14

POSITIVE LOGITS

rana

0.18

unta

0.17

ctxt

0.15

wart

0.15

ycastle

0.15

edList

0.15

vÃ¤

0.14

à¸·à¸Ńà¸Ķ

0.14

__,__

0.14

Activations Density 0.075%

instances of reported speech or statements in the text

No Comments

No Known Activations