INDEX

Explanations

words related to social injustice and marginalization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Å¡em

-0.17

unsch

-0.16

uzzi

-0.16

ceptors

-0.14

urally

-0.14

lical

-0.14

amed

-0.14

sto

-0.14

ddy

-0.13

Î´ÏģÎ¿

-0.13

POSITIVE LOGITS

/dis

0.22

(dis

0.19

dis

0.19

Dis

0.18

Dis

0.18

Ĥæķ°

0.17

zell

0.17

zung

0.17

.dis

0.17

-dis

0.16

Activations Density 0.031%

words related to social injustice and marginalization

No Comments

No Known Activations