INDEX

Explanations

punctuation marks and parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

borg

-0.15

ula

-0.15

-*-

-0.15

ameda

-0.14

ä»Ĭ

-0.14

pra

-0.13

ingly

-0.13

 schemes

-0.13

 coroutine

-0.13

 Bias

-0.13

POSITIVE LOGITS

Soup

0.15

 tarif

0.15

.eval

0.14

Dash

0.14

iggs

0.14

IDX

0.14

Facade

0.14

eÄį

0.14

à¸´à¹ī

0.14

olg

0.13

Activations Density 0.013%

punctuation marks and parentheses

No Comments

No Known Activations