INDEX

Explanations

references to secrets and hidden information

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

Ã¼nkÃ¼

-0.15

eo

-0.15

OPTIONS

-0.13

ÙĪÙĨØ¯

-0.13

ayo

-0.13

Pragma

-0.13

acia

-0.13

Ð¶Ðµ

-0.13

-0.12

POSITIVE LOGITS

 secret

0.77

 secrets

0.73

 Secret

0.60

secret

0.60

 Secrets

0.58

ç§ĺ

0.57

-secret

0.56

Secret

0.56

 SECRET

0.55

 secre

0.53

Activations Density 0.196%

references to secrets and hidden information

No Comments

No Known Activations