INDEX

Explanations

content related to sexual orientation, identity, or expression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.15

pread

-0.15

å¹

-0.14

CKER

-0.14

oste

-0.14

ãĥģãĥ¥

-0.14

Ã¡Äį

-0.14

CLA

-0.13

Ð¾ÑĢÐ¾Ð²

-0.13

çļĦäºĭ

-0.13

POSITIVE LOGITS

akan

0.18

aur

0.16

RowIndex

0.15

 Provid

0.14

 status

0.14

 select

0.14

attr

0.14

ahn

0.13

unken

0.13

 Status

0.13

Activations Density 0.008%

content related to sexual orientation, identity, or expression

No Comments

No Known Activations