INDEX

Explanations

references to actors and their roles in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ader

-0.19

erable

-0.19

erator

-0.18

est

-0.18

ned

-0.17

seo

-0.16

coming

-0.16

eration

-0.16

Acts

-0.15

POSITIVE LOGITS

uate

0.20

-direct

0.19

roles

0.19

 roles

0.18

 Roles

0.18

/music

0.18

uated

0.17

/model

0.17

/wait

0.16

uating

0.16

Activations Density 0.013%

references to actors and their roles in various contexts

No Comments

No Known Activations