INDEX

Explanations

references to taking on challenges or responsibilities

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

Negative Logits

wyn

-0.18

cki

-0.15

irie

-0.15

zan

-0.15

zt

-0.14

qui

-0.14

andon

-0.14

entifier

-0.14

ddy

-0.13

vido

-0.13

POSITIVE LOGITS

mÃŃ

0.15

 tackle

0.14

 é¦

0.14

 attitude

0.14

erus

0.14

mute

0.14

äººæ°Ĺ

0.14

itel

0.14

iton

0.13

FT

0.13

Activations Density 0.044%

references to taking on challenges or responsibilities

No Known Activations