INDEX

Explanations

references to male 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 @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

swick

-0.18

.au

-0.16

Ã¡ÅĻ

-0.16

cÃ¼

-0.16

HING

-0.15

 defaultCenter

-0.15

egin

-0.15

ibold

-0.14

 '../../../../../

-0.14

iks

-0.14

POSITIVE LOGITS

/g

0.27

liner

0.19

iac

0.17

hattan

0.16

ana

0.16

who

0.16

/entities

0.16

Alv

0.15

-next

0.15

Activations Density 0.032%

references to male individuals or groups

No Comments

No Known Activations