INDEX

Explanations

references to kidnapping and abductions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

REFIX

-0.17

ãĥĥãĥĹ

-0.17

%f

-0.15

 destroying

-0.15

 misdemean

-0.14

ipple

-0.14

ê²©

-0.14

icipant

-0.14

estate

-0.14

alty

-0.13

POSITIVE LOGITS

kid

0.77

Kid

0.76

Kid

0.69

kid

0.68

 kidnapping

0.57

 kidn

0.57

 kidnapped

0.54

 abduction

0.48

 abducted

0.46

 kidney

0.43

Activations Density 0.103%

references to kidnapping and abductions

No Comments

No Known Activations