INDEX

Explanations

references to the character Hanuman

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ourg

-0.18

field

-0.16

abbo

-0.15

 kick

-0.15

PBS

-0.15

ietet

-0.15

 meshes

-0.14

oq

-0.14

ÑĤÐµÑĢ

-0.14

Ø§Ø±Ø©

-0.14

POSITIVE LOGITS

errupt

0.16

Ã²i

0.15

lesia

0.15

statt

0.15

 Spor

0.15

kenin

0.14

DataURL

0.14

ussed

0.14

Yii

0.14

éĻ

0.14

Activations Density 0.037%

references to the character Hanuman

No Comments

No Known Activations