INDEX

Explanations

names of political leaders and government officials

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

Å¡ti

-0.18

ÃľM

-0.16

yasal

-0.15

à¸£à¸ª

-0.14

yar

-0.14

à¸²à¸ĩà¸§

-0.14

gesi

-0.14

lsen

-0.14

MethodInfo

-0.14

.pix

-0.14

POSITIVE LOGITS

xit

0.16

emoc

0.14

ief

0.14

 Huntington

0.14

 meshes

0.14

0.13

 Hint

0.13

 aide

0.13

 Ping

0.13

Activations Density 0.278%

names of political leaders and government officials

No Comments

No Known Activations