INDEX

Explanations

references to professional roles and career experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ocoder

-0.15

DataMember

-0.14

bl

-0.14

 Female

-0.14

ift

-0.14

 female

-0.14

ges

-0.13

fone

-0.13

oro

-0.13

POSITIVE LOGITS

 lawy

0.25

 software

0.23

 lawyers

0.22

 engineering

0.20

 sales

0.20

 lawyer

0.20

 insurance

0.20

 Software

0.20

 civil

0.19

 marketing

0.19

Activations Density 0.320%

references to professional roles and career experiences

No Comments

No Known Activations