INDEX

Explanations

specific characters or symbols used in digital content

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

 Oracle

-0.14

Optimizer

-0.14

 supported

-0.14

 Darling

-0.14

ascal

-0.14

 royal

-0.13

 Charlotte

-0.13

 supporting

-0.13

 princess

-0.13

 Netflix

-0.13

POSITIVE LOGITS

JFK

0.22

 Ethnic

0.18

 Fucked

0.16

Industrial

0.16

 musique

0.16

 Electronics

0.15

 Industrial

0.15

_noise

0.15

 electronics

0.15

 Rape

0.15

Activations Density 0.003%

specific characters or symbols used in digital content

No Comments

No Known Activations