INDEX

Explanations

instances of posting or attribution in written content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 rencont

-0.14

stin

-0.14

ÙĦÙĪØ¯

-0.14

ustum

-0.14

®

-0.14

Ø¨ÙĬÙĨ

-0.14

iteli

-0.14

icast

-0.13

 nostalg

-0.13

Ð¾Ð²Ð°ÑĤÐµÐ»ÑĮ

-0.13

POSITIVE LOGITS

igure

0.17

ania

0.16

idor

0.16

 Mang

0.15

Ã¡o

0.15

 Weinstein

0.14

ilin

0.14

eut

0.14

uran

0.14

_UNUSED

0.14

Activations Density 0.022%

instances of posting or attribution in written content

No Comments

No Known Activations