INDEX

Explanations

numeric identifiers and references in the text

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

oby

-0.16

vil

-0.15

ªĮ

-0.14

á»Ŀ

-0.14

aven

-0.14

ubo

-0.14

º«

-0.14

plash

-0.14

 Raven

-0.13

ä¾ĽåºĶ

-0.13

POSITIVE LOGITS

0.57

0.56

0.55

0.54

0.53

Activations Density 0.028%

numeric identifiers and references in the text

No Comments

No Known Activations