INDEX

Explanations

expressions of concern or support within conversations

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

ileo

-0.16

agnostic

-0.15

igm

-0.15

igt

-0.15

Ã¡j

-0.15

dej

-0.15

ade

-0.15

amura

-0.14

elaide

-0.14

iggins

-0.14

POSITIVE LOGITS

me

0.17

 Ment

0.16

 your

0.16

istrovstvÃŃ

0.15

orie

0.15

æ®µ

0.15

icamente

0.14

Monkey

0.14

tob

0.14

esini

0.14

Activations Density 0.220%

expressions of concern or support within conversations

No Comments

No Known Activations