INDEX

Explanations

references to gender, particularly related to men

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

er

-0.20

tica

-0.19

eriod

-0.18

engin

-0.18

erif

-0.17

erin

-0.16

dete

-0.16

erde

-0.16

ted

-0.16

agini

-0.15

POSITIVE LOGITS

folk

0.49

opause

0.46

aces

0.38

ial

0.38

ager

0.35

aced

0.34

ials

0.33

/w

0.33

's

0.31

fol

0.30

Activations Density 0.034%

references to gender, particularly related to men

No Comments

No Known Activations