INDEX

Explanations

instances of the word "and."

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

Not in Any Lists

No Comments

Negative Logits

 isolation

-0.17

 retention

-0.15

ention

-0.15

 ours

-0.15

iced

-0.15

 Common

-0.15

ä¹ĭ

-0.14

Configurer

-0.14

 Hobby

-0.14

POSITIVE LOGITS

isque

0.16

agina

0.16

quete

0.15

ombo

0.15

bÃŃ

0.15

ÐºÐ¾ÑĤ

0.15

 allies

0.15

mÃ©

0.14

ocale

0.14

 alliances

0.14

Activations Density 0.000%

instances of the word "and."

No Comments

No Known Activations