INDEX

Explanations

phrases related to compliance and guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

deer

-0.17

ARRY

-0.17

arry

-0.16

inspace

-0.15

agens

-0.14

swire

-0.14

ile

-0.14

ovit

-0.14

\grid

-0.14

hift

-0.14

POSITIVE LOGITS

usan

0.16

itas

0.15

 Hend

0.14

GU

0.14

.opend

0.14

inos

0.13

ovice

0.13

 Flower

0.13

Ch

0.13

 dÆ°

0.13

Activations Density 0.039%

phrases related to compliance and guidelines

No Comments

No Known Activations