INDEX

Explanations

URLs and web links present in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Shutterstock

-0.17

iller

-0.17

Ã±o

-0.15

Ã¥r

-0.15

chn

-0.15

ÃŃf

-0.14

 Blasio

-0.14

.histogram

-0.14

Î³ÏģÎ¬

-0.14

jsc

-0.13

POSITIVE LOGITS

egin

0.18

undi

0.16

estar

0.15

undy

0.14

Ð»ÑıÑħ

0.14

ewe

0.14

estic

0.14

DELAY

0.13

é¦

0.13

ris

0.13

Activations Density 0.019%

URLs and web links present in the text

No Comments

No Known Activations