INDEX

Explanations

references to political figures and their statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ÙĩÙĦ

-0.16

ago

-0.15

scription

-0.15

zee

-0.15

Ðĭ

-0.14

inscription

-0.14

æĭį

-0.14

.Preference

-0.13

ark

-0.13

 Voter

-0.13

POSITIVE LOGITS

anner

0.16

opers

0.15

xab

0.15

nav

0.15

uml

0.14

 saber

0.14

rea

0.14

 Desire

0.14

åĨ

0.13

á»Ļ

0.13

Activations Density 0.077%

references to political figures and their statements

No Comments

No Known Activations