INDEX

Explanations

descriptive adjectives and phrases that convey various levels of intensity or complexity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ued

-0.17

ossa

-0.17

éľ

-0.17

è¼Ķ

-0.15

eno

-0.15

 olan

-0.14

isbury

-0.14

UGIN

-0.14

izio

-0.13

Ð±Ð°Ð²

-0.13

POSITIVE LOGITS

ernity

0.14

/****************************************************************************↵

0.14

strup

0.14

uez

0.14

 Kosten

0.14

cies

0.13

ctxt

0.13

 Lloyd

0.13

stances

0.13

omin

0.13

Activations Density 0.351%

descriptive adjectives and phrases that convey various levels of intensity or complexity

No Comments

No Known Activations