INDEX

Explanations

phrases indicating the absence of something

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

atching

-0.16

imum

-0.15

 ÅĻÃŃj

-0.15

scribe

-0.14

kop

-0.14

ForRow

-0.14

jev

-0.14

Ð½ÐµÐ´

-0.13

ÄĻd

-0.13

atcher

-0.13

POSITIVE LOGITS

 doubt

0.28

abox

0.26

 Borders

0.20

 fail

0.20

 exception

0.20

Borders

0.19

 question

0.18

Bias

0.18

 prejudice

0.18

 regard

0.17

Activations Density 0.037%

phrases indicating the absence of something

No Comments

No Known Activations