INDEX

Explanations

phrases related to legal proceedings and accusations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-0.15

ayah

-0.15

zcze

-0.15

Neighbor

-0.15

iid

-0.14

favor

-0.14

nostic

-0.14

udem

-0.14

entiful

-0.14

zel

-0.14

POSITIVE LOGITS

ithe

0.15

 photoc

0.14

erva

0.14

 aborted

0.14

 iron

0.14

Ip

0.14

 totally

0.13

èķ

0.13

 myself

0.13

 Guinness

0.13

Activations Density 0.003%

phrases related to legal proceedings and accusations

No Comments

No Known Activations