INDEX

Explanations

references to security, enforcement agencies, and border control

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 GiÃ¡o

-0.17

bane

-0.15

esome

-0.15

Dig

-0.14

sÃŃ

-0.14

TEE

-0.14

alm

-0.14

onth

-0.13

Dra

-0.13

Dig

-0.13

POSITIVE LOGITS

 Immigration

0.35

 Border

0.34

 immigration

0.30

Border

0.30

 Customs

0.29

 border

0.29

 BORDER

0.28

Imm

0.27

ICE

0.25

 Homeland

0.25

Activations Density 0.025%

references to security, enforcement agencies, and border control

No Comments

No Known Activations