INDEX

Explanations

mentions and variations of the word "like" as well as forms of the word "licorice."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

agn

-0.17

awai

-0.16

indr

-0.15

Ø¹Ø§Øª

-0.14

ÑģÑĤÐ°Ð½

-0.14

napshot

-0.14

 æ±

-0.14

 å¸Ĥ

-0.14

ropol

-0.13

ocket

-0.13

POSITIVE LOGITS

Ä±lÄ±Ã§

0.19

entious

0.17

utenant

0.17

berman

0.17

udit

0.17

ardy

0.16

ensed

0.15

infeld

0.15

Datum

0.15

ensi

0.15

Activations Density 0.029%

mentions and variations of the word "like" as well as forms of the word "licorice."

No Comments

No Known Activations