INDEX

Explanations

phrases related to threats and acts of violence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

_traits

-0.16

lobs

-0.15

ignet

-0.15

ilio

-0.15

 hÆ°á»Łng

-0.14

itched

-0.14

ziel

-0.14

ifo

-0.14

allee

-0.14

POSITIVE LOGITS

 threats

0.26

 threat

0.26

 threatening

0.25

 threatened

0.24

threat

0.24

 Threat

0.23

 threaten

0.23

 threatens

0.22

-threat

0.22

 intimidation

0.18

Activations Density 0.044%

phrases related to threats and acts of violence

No Comments

No Known Activations