INDEX

Explanations

references to political and legislative processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

esome

-0.18

iyim

-0.17

adro

-0.16

loquent

-0.15

ÙĦÙĬÙĩ

-0.15

nock

-0.15

aticon

-0.14

serter

-0.14

asers

-0.14

vanced

-0.14

POSITIVE LOGITS

icie

0.14

agine

0.14

ong

0.14

Sne

0.13

Sno

0.13

aven

0.13

 Notes

0.13

Ùģ

0.13

Activations Density 0.044%

references to political and legislative processes

No Comments

No Known Activations