INDEX

Explanations

references to employment and job roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

decade

-0.15

forge

-0.14

tober

-0.14

Ð·Ñĭ

-0.14

far

-0.14

 tonight

-0.14

 Joint

-0.14

 DÃ¼n

-0.14

 Tonight

-0.13

 strokeWidth

-0.13

POSITIVE LOGITS

 part

0.20

half

0.18

 flex

0.17

 half

0.17

 full

0.17

 flexible

0.16

part

0.16

-full

0.16

 halftime

0.16

 Spor

0.16

Activations Density 0.095%

references to employment and job roles

No Comments

No Known Activations