INDEX

Explanations

words related to government policies and legal regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

iosper

-0.15

.ide

-0.15

oS

-0.14

iece

-0.13

ddit

-0.13

åİļ

-0.13

 gratuites

-0.13

ackers

-0.13

\Mapping

-0.13

jal

-0.13

POSITIVE LOGITS

 tender

0.16

ãģĵãģĿ

0.15

insula

0.15

ìĤ¬ì§Ģ

0.14

âĢ¦the

0.14

 Tender

0.14

 relief

0.14

div

0.14

[,]

0.14

Activations Density 0.372%

words related to government policies and legal regulations

No Comments

No Known Activations