INDEX

Explanations

references to political processes and insider activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ilda

-0.17

igm

-0.15

 wishlist

-0.14

'//

-0.14

 decrease

-0.14

Ã¼z

-0.13

cela

-0.13

erca

-0.13

'[

-0.13

POSITIVE LOGITS

iffies

0.16

 Burnett

0.15

åı

0.15

 migrationBuilder

0.15

IH

0.14

 Team

0.14

 addCriterion

0.14

ebi

0.14

unca

0.14

ÑģÐº

0.13

Activations Density 0.000%

references to political processes and insider activities

No Comments

No Known Activations