INDEX

Explanations

references to social identities and their implications in societal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Facing

-0.15

åĭĴ

-0.15

itten

-0.14

elp

-0.14

preview

-0.14

anse

-0.14

imet

-0.13

.isNull

-0.13

utr

-0.13

lington

-0.13

POSITIVE LOGITS

equ

0.36

ä»¥ä¸º

0.30

 think

0.29

 mistake

0.29

 thinks

0.28

 assumes

0.27

 associate

0.26

think

0.26

 assume

0.25

 associates

0.25

Activations Density 0.630%

references to social identities and their implications in societal contexts

No Comments

No Known Activations