INDEX

Explanations

phrases and concepts related to responsibility and ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Ø³ØªÙħ

-0.16

opr

-0.16

ystone

-0.16

ONO

-0.15

\base

-0.15

swer

-0.15

hower

-0.15

esti

-0.14

ngle

-0.14

ono

-0.14

POSITIVE LOGITS

qus

0.15

PAIR

0.14

pap

0.14

Î³Î¿Ïģ

0.14

Pap

0.14

EMP

0.14

Hos

0.14

xFFFFFF

0.14

uyá»ĩt

0.14

zo

0.13

Activations Density 0.009%

phrases and concepts related to responsibility and ownership

No Comments

No Known Activations