INDEX

Explanations

pronouns related to individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 itself

-0.17

taire

-0.15

onaut

-0.15

ayne

-0.14

Ã¯

-0.14

pom

-0.14

purple

-0.14

ibel

-0.14

isma

-0.14

POSITIVE LOGITS

/us

0.38

/her

0.35

self

0.26

zelf

0.25

SELF

0.25

/th

0.23

iner

0.21

atically

0.20

-mÃªme

0.20

chy

0.19

Activations Density 0.155%

pronouns related to individuals or groups

No Comments

No Known Activations