INDEX

Explanations

phrases related to criminal activities and investigations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 dames

-0.13

/the

-0.13

ught

-0.13

ishment

-0.13

any

-0.12

ceil

-0.12

innen

-0.12

 vÃŃde

-0.12

łí

-0.12

assic

-0.12

POSITIVE LOGITS

orex

0.16

‘

0.15

unsch

0.15

 latest

0.14

draul

0.14

elden

0.13

avig

0.13

gov

0.13

ÂŃt

0.13

Activations Density 0.277%

phrases related to criminal activities and investigations

No Comments

No Known Activations