INDEX

Explanations

references to law enforcement and firearms training

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

aight

-0.16

ÐµÑĢÐµÑĩ

-0.15

ä¿®

-0.15

geh

-0.15

oire

-0.14

OUCH

-0.14

 Missile

-0.14

abbo

-0.14

bjerg

-0.14

POSITIVE LOGITS

 standoff

0.19

 hostage

0.18

 negotiation

0.18

 negotiated

0.18

 Negot

0.17

 vests

0.17

 hostages

0.17

egot

0.17

 siege

0.15

 warrants

0.15

Activations Density 0.088%

references to law enforcement and firearms training

No Comments

No Known Activations