INDEX

Explanations

phrases indicating action and participation

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

ÎµÏĢ

-0.17

-0.16

 ChÃŃ

-0.16

ftware

-0.15

fir

-0.14

enti

-0.14

rzy

-0.14

 MÃľ

-0.14

mrt

-0.14

íĴ

-0.14

POSITIVE LOGITS

éĴ

0.18

run

0.16

 subsequ

0.15

æľĽ

0.15

ebo

0.15

 incons

0.14

amon

0.14

-Trump

0.14

ilated

0.14

ycop

0.14

Activations Density 0.420%

phrases indicating action and participation

No Comments

No Known Activations