INDEX

Explanations

URLs and code snippets related to article links

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ittal

-0.16

zilla

-0.15

lica

-0.15

Ø¯Ø§

-0.15

ombo

-0.15

annie

-0.15

ÙĪØ§ÙĨ

-0.14

Ã©rc

-0.14

aper

-0.14

arkan

-0.14

POSITIVE LOGITS

oro

0.15

 Silk

0.15

ALIGN

0.15

cow

0.14

wert

0.14

Cow

0.14

artner

0.14

oz

0.13

Î¼ÎµÎ½

0.13

orney

0.13

Activations Density 0.242%

URLs and code snippets related to article links

No Comments

No Known Activations