INDEX

Explanations

terms related to crime and legal proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Matchers

-0.16

wed

-0.15

aty

-0.15

Ã¢b

-0.15

lyph

-0.15

ubl

-0.15

arters

-0.15

riday

-0.15

ebo

-0.15

loadModel

-0.14

POSITIVE LOGITS

bes

0.15

jee

0.14

á»Ľt

0.14

illo

0.13

IRM

0.13

leet

0.13

itter

0.13

RG

0.13

Activations Density 0.136%

terms related to crime and legal proceedings

No Comments

No Known Activations