INDEX

Explanations

references to law enforcement actions, particularly their use of force during protests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Äĵ

-0.16

enha

-0.15

agu

-0.15

ngÃ¶r

-0.15

stab

-0.15

Ð³Ð»Ñı

-0.14

Î³Î³

-0.14

eous

-0.14

bote

-0.14

-syntax

-0.14

POSITIVE LOGITS

 tear

0.25

 dispers

0.22

éİ®

0.20

 police

0.19

 Tear

0.19

 deployed

0.18

Deploy

0.18

 cops

0.18

deploy

0.18

 dispersion

0.18

Activations Density 0.062%

references to law enforcement actions, particularly their use of force during protests

No Comments

No Known Activations