INDEX

Explanations

references to killing or murder

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

orial

-0.15

esta

-0.14

olina

-0.14

aux

-0.14

 cred

-0.14

omaly

-0.14

 Jord

-0.14

 hollow

-0.13

laÅŁ

-0.13

acles

-0.13

POSITIVE LOGITS

ambi

0.17

abyrin

0.17

/renderer

0.15

iani

0.15

ouser

0.15

/goto

0.15

ustr

0.15

IVEN

0.15

ifestyles

0.14

Activations Density 0.029%

references to killing or murder

No Comments

No Known Activations