INDEX

Explanations

first-person and inclusive pronouns indicating personal or shared experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Ø±ÛĮØ²

-0.15

mÃ¼r

-0.14

Ø§ÙĬØª

-0.14

eree

-0.14

unci

-0.14

.getOwnProperty

-0.14

 Ð½ÐµÑĤ

-0.14

à¸³

-0.13

 lazÄ±m

-0.13

 gonna

-0.13

POSITIVE LOGITS

've

0.71

’ve

0.63

ve

0.53

Ive

0.40

ive

0.35

ve

0.33

VE

0.33

Ve

0.32

_ve

0.32

 ÄĳÃ£

0.31

Activations Density 0.238%

first-person and inclusive pronouns indicating personal or shared experiences

No Comments

No Known Activations

first-person and inclusive pronouns indicating personal or shared experiences

No Comments

No Known Activations