INDEX

Explanations

references to judicial and law enforcement bodies or concepts

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

 diss

-0.15

 help

-0.14

íĭĢ

-0.14

tplib

-0.14

Ø¬ÙĦ

-0.13

tl

-0.13

the

-0.13

InOut

-0.13

sm

-0.13

éĻħ

-0.13

POSITIVE LOGITS

 Association

0.20

 Company

0.20

 Society

0.19

 Museum

0.18

 Foundation

0.18

 Corporation

0.17

 Agency

0.17

 Orchestra

0.17

 Council

0.16

 Commission

0.16

Activations Density 0.188%

references to judicial and law enforcement bodies or concepts

No Comments

No Known Activations