INDEX

Explanations

positive and descriptive language related to creative activities and crafting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

canf

-0.15

jev

-0.14

FromBody

-0.14

ento

-0.14

Ð½Ñı

-0.14

Gap

-0.14

ingroup

-0.14

\Table

-0.13

\Bridge

-0.13

culos

-0.13

POSITIVE LOGITS

 scrap

0.31

 Layout

0.29

 journal

0.29

 layout

0.28

Layout

0.27

 layouts

0.27

 Journal

0.26

 Scrap

0.26

journal

0.26

layout

0.25

Activations Density 0.034%

positive and descriptive language related to creative activities and crafting

No Comments

No Known Activations