INDEX

Explanations

themes related to suspicion and investigation into potential crimes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ungan

-0.15

ocaly

-0.14

ocha

-0.14

zew

-0.14

solete

-0.14

áº¡

-0.14

wax

-0.13

.ExecuteScalar

-0.13

Ð±Ð¸Ð½

-0.13

angu

-0.13

POSITIVE LOGITS

 suspect

0.87

Sus

0.81

 suspects

0.79

sus

0.78

 suspicion

0.75

Sus

0.73

sus

0.73

 Susp

0.70

 suspected

0.69

 suspicions

0.68

Activations Density 0.195%

themes related to suspicion and investigation into potential crimes

No Comments

No Known Activations

themes related to suspicion and investigation into potential crimes

No Comments

No Known Activations