INDEX

Explanations

inquiries about personal experiences and preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

lesia

-0.16

Ð½Ð°ÑĢ

-0.15

statuses

-0.14

tober

-0.14

elm

-0.14

ioni

-0.14

 identities

-0.14

éŁ¿

-0.14

ober

-0.13

ientes

-0.13

POSITIVE LOGITS

 favourite

0.15

ikat

0.15

pet

0.15

ETA

0.15

Jur

0.14

Ð°ÐµÐ¼

0.14

okrat

0.14

favorite

0.14

_favorite

0.14

fav

0.13

Activations Density 0.043%

inquiries about personal experiences and preferences

No Comments

No Known Activations