INDEX

Explanations

descriptions of property features and amenities

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

-0.16

aug

-0.15

 leve

-0.15

 rumor

-0.14

liv

-0.14

Programming

-0.13

ivec

-0.13

TypeId

-0.13

jab

-0.13

idden

-0.13

POSITIVE LOGITS

 conserv

0.20

 fitted

0.20

WC

0.19

 integral

0.19

Vel

0.18

 Utility

0.18

 airing

0.18

integral

0.18

WC

0.17

bi

0.17

Activations Density 0.028%

descriptions of property features and amenities

No Comments

No Known Activations