INDEX

Explanations

references to significant quantities and measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Î²Î¿Î»

-0.16

TypeInfo

-0.15

Henry

-0.15

roof

-0.15

 Solic

-0.14

ÑĢÑĥÐ±

-0.14

_traits

-0.14

wdx

-0.14

emons

-0.14

ittings

-0.14

POSITIVE LOGITS

acers

0.16

ernet

0.16

Ã¡p

0.15

raith

0.15

rij

0.14

TV

0.14

po

0.14

ay

0.14

Bij

0.14

æŃ

0.14

Activations Density 0.016%

references to significant quantities and measures

No Comments

No Known Activations