INDEX

Explanations

references to political actions and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

auge

-0.16

kola

-0.15

Ð»Ð°Ð´Ð°

-0.15

orgen

-0.15

baugh

-0.14

 PROCUREMENT

-0.14

rand

-0.14

wear

-0.14

Jun

-0.14

eba

-0.14

POSITIVE LOGITS

aravel

0.16

Ã¤ng

0.15

urum

0.15

ayi

0.14

malink

0.14

avier

0.14

 Burl

0.14

istrovstvÃŃ

0.13

/generated

0.13

ci

0.13

Activations Density 1.492%

references to political actions and their implications

No Comments

No Known Activations