INDEX

Explanations

references to public broadcasting entities and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

udo

-0.17

ulen

-0.17

-0.15

ibrary

-0.15

mo

-0.15

mnt

-0.15

mdat

-0.15

DD

-0.15

ÐľÐŀ

-0.14

ÂłM

-0.14

POSITIVE LOGITS

ãĥı

0.19

icha

0.18

heimer

0.18

-H

0.18

lotte

0.18

hec

0.17

à¹Ģà¸®

0.17

-h

0.16

'H

0.16

ì²ĺ

0.16

Activations Density 0.035%

references to public broadcasting entities and organizations

No Comments

No Known Activations