INDEX

Explanations

terms and phrases related to advocacy and support for various issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

stad

-0.15

/MPL

-0.15

Î®ÏĤ

-0.14

 Gould

-0.14

nah

-0.14

lemen

-0.14

iffin

-0.14

vette

-0.14

erer

-0.14

Ø¯

-0.14

POSITIVE LOGITS

HORT

0.17

 Tradable

0.17

 wings

0.15

0.14

opoulos

0.14

 Miles

0.14

plusplus

0.14

unto

0.14

 Belt

0.14

 Colleg

0.13

Activations Density 0.012%

terms and phrases related to advocacy and support for various issues

No Comments

No Known Activations