INDEX

Explanations

content related to violent incidents or attacks

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

legg

-0.17

agine

-0.17

raci

-0.16

turnstile

-0.16

ingleton

-0.16

.connector

-0.15

rawer

-0.15

ght

-0.15

astos

-0.15

umer

-0.14

POSITIVE LOGITS

 latest

0.17

idon

0.17

andro

0.17

iden

0.15

Ð»ÑĥÐ±

0.14

REMOTE

0.14

asso

0.14

iya

0.14

à¹Ģà¸ł

0.14

Activations Density 0.023%

content related to violent incidents or attacks

No Comments

No Known Activations