INDEX

Explanations

links to images and websites

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ZO

-0.15

fak

-0.14

fillType

-0.14

immel

-0.14

Ø³Ø§Ø³

-0.14

 Blades

-0.14

rada

-0.14

 defaults

-0.14

oldem

-0.14

ipes

-0.14

POSITIVE LOGITS

://

0.20

Res

0.16

0.14

arm

0.13

oux

0.13

 Flat

0.13

_Res

0.13

Aug

0.13

LATED

0.13

Activations Density 0.003%

links to images and websites

No Comments

No Known Activations