INDEX

Explanations

references to political context and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Ã¢

-0.23

 Ãİ

-0.22

ÃĤ

-0.19

Ãİ

-0.16

 ÃĤ

-0.15

Ã¢

-0.14

Ø¦

-0.13

↵

-0.13

etc

-0.13

POSITIVE LOGITS

.bunifuFlatButton

0.21

 âĢº

0.18

ActionCreators

0.15

-:-

0.14

 frau

0.14

/WebAPI

0.14

 luder

0.14

 Shemale

0.14

ynamo

0.13

 âĵĺ

0.13

Activations Density 0.026%

references to political context and interactions

No Comments

No Known Activations