INDEX

Explanations

references to HTML elements or coding syntax in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

TINGS

-0.15

amas

-0.15

 Corm

-0.14

istrovstvÃŃ

-0.14

ji

-0.14

Ð¼ÐµÑĩ

-0.14

INGLE

-0.14

'gc

-0.14

WARDED

-0.14

-0.13

POSITIVE LOGITS

CIA

0.18

 mass

0.16

 symbol

0.15

 Negro

0.15

 Herr

0.15

 massa

0.14

 Lucifer

0.14

Recovered

0.14

 Bilder

0.14

Sat

0.14

Activations Density 0.000%

references to HTML elements or coding syntax in text

No Comments

No Known Activations