INDEX

Explanations

mentions of people in professional contexts or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Agencies

-0.16

ãĥ¼ãĥį

-0.14

achers

-0.14

åĭŁ

-0.14

.gov

-0.13

atha

-0.13

æ³ķéĻ¢

-0.13

isper

-0.13

acher

-0.13

ancer

-0.13

POSITIVE LOGITS

 director

0.62

 Director

0.60

 chief

0.56

CEO

0.54

 Chief

0.51

 vice

0.50

 president

0.50

director

0.49

 head

0.49

Director

0.49

Activations Density 1.065%

mentions of people in professional contexts or roles

No Comments

No Known Activations