INDEX

Explanations

references to male individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ese

-0.15

etri

-0.15

rezent

-0.14

adolu

-0.14

edian

-0.13

itte

-0.13

ÐĿÐĨ

-0.13

ientes

-0.13

ately

-0.13

ient

-0.13

POSITIVE LOGITS

erva

0.18

ekyll

0.17

isphere

0.16

vise

0.16

/she

0.15

sett

0.14

ixmap

0.14

strap

0.14

.Syntax

0.14

erta

0.14

Activations Density 0.023%

references to male individuals

No Comments

No Known Activations