INDEX

Explanations

references to historical crimes and significant criminal events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ertino

-0.16

Ð»ÐµÐ¼

-0.16

 Refugee

-0.14

Ð¼ÐµÑĩ

-0.14

 embargo

-0.14

swick

-0.13

visa

-0.13

ÙĨÙĬÙĨ

-0.13

isay

-0.13

asant

-0.13

POSITIVE LOGITS

 murders

0.41

 killings

0.38

 killers

0.38

 killer

0.36

 murder

0.35

 murdered

0.35

 murderer

0.35

 murdering

0.35

 killing

0.35

 serial

0.34

Activations Density 0.087%

references to historical crimes and significant criminal events

No Comments

No Known Activations