INDEX

Explanations

references to legal or judicial proceedings

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

 Generation

-0.17

adele

-0.15

.struts

-0.15

eyh

-0.15

readcr

-0.14

 generation

-0.14

 Hurt

-0.14

onta

-0.14

Ã³c

-0.14

 plagiar

-0.14

POSITIVE LOGITS

anÄ±

0.14

osg

0.14

 Vide

0.14

Capabilities

0.14

hire

0.14

æ½®

0.14

 blows

0.14

Animations

0.14

 unlocks

0.13

uz

0.13

Activations Density 0.025%

references to legal or judicial proceedings

No Comments

No Known Activations