INDEX

Explanations

references to elections and elected officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

stre

-0.17

lector

-0.17

thing

-0.17

ÑģÑĤÐ¸

-0.17

lichkeit

-0.16

iola

-0.16

laÅŁ

-0.16

artz

-0.15

stract

-0.15

åĪĹ

-0.14

POSITIVE LOGITS

 officials

0.22

 Officials

0.20

/app

0.20

eer

0.18

ees

0.17

Officials

0.17

ors

0.16

AVA

0.16

 representatives

0.15

Activations Density 0.015%

references to elections and elected officials

No Comments

No Known Activations