INDEX

Explanations

references to law enforcement agencies, particularly in a governmental or legal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

.hw

-0.16

mental

-0.15

arna

-0.15

ates

-0.15

 Spirits

-0.14

entai

-0.14

alus

-0.14

xab

-0.13

ering

-0.13

 fertil

-0.13

POSITIVE LOGITS

vio

0.16

lio

0.15

asaki

0.15

aland

0.15

Å¾ÃŃ

0.14

UInteger

0.14

riger

0.14

ÅĻÃŃ

0.14

à¸ĩà¸Ĥ

0.14

 Giá»Ľi

0.14

Activations Density 0.268%

references to law enforcement agencies, particularly in a governmental or legal context

No Comments

No Known Activations