INDEX

Explanations

references to individuals and specific organizations in a text

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

-0.17

 Moor

-0.17

/mp

-0.16

.mozilla

-0.16

 Moody

-0.15

amedi

-0.15

Mesh

-0.15

 nÃ¡d

-0.15

iske

-0.14

Meg

-0.14

POSITIVE LOGITS

 Martin

1.34

 martin

1.24

Martin

1.20

 MART

1.18

 mart

1.14

mart

1.09

 Mart

1.08

 Martins

1.03

Mart

1.00

-Mart

0.93

Activations Density 0.111%

references to individuals and specific organizations in a text

No Known Activations