INDEX

Explanations

disclaimers or caveats regarding information not being legal or medical advice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ubar

-0.16

eba

-0.14

Exist

-0.14

isky

-0.14

_ANAL

-0.14

Ð°Ð¶

-0.13

å¹¹ç·ļ

-0.13

icy

-0.13

urch

-0.13

udent

-0.13

POSITIVE LOGITS

nor

0.24

 endorse

0.24

 endorsement

0.23

 guarantee

0.23

 endorsed

0.21

 exhaustive

0.21

nor

0.21

 endorsements

0.20

 endorsing

0.19

 guarante

0.19

Activations Density 0.155%

disclaimers or caveats regarding information not being legal or medical advice

No Comments

No Known Activations