INDEX

Explanations

expressions of caution or concern in interpersonal interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 somewhat

-0.16

 somew

-0.16

Ãłnh

-0.15

StackNavigator

-0.15

hyp

-0.15

asso

-0.14

á»ĭ

-0.14

uty

-0.14

 rather

-0.14

 instead

-0.14

POSITIVE LOGITS

 anymore

0.26

TOO

0.23

too

0.22

too

0.20

Too

0.20

Too

0.19

å¤ª

0.19

 unless

0.18

ä»»ä½ķ

0.18

Ã¤tze

0.17

Activations Density 0.126%

expressions of caution or concern in interpersonal interactions

No Comments

No Known Activations