INDEX

Explanations

terms related to angles and their measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

chyb

-0.15

Î³Î¼Î±

-0.15

ourg

-0.14

apus

-0.14

ÐµÑĩÐµÐ½Ð¸Ðµ

-0.14

è¡ĮæĶ¿

-0.14

actics

-0.14

èĻ

-0.14

.addObject

-0.14

elow

-0.14

POSITIVE LOGITS

 angles

0.17

.Debugger

0.15

 humble

0.14

èı

0.14

inc

0.14

..

0.13

 catalogs

0.13

Ang

0.13

 wheel

0.13

 invariant

0.13

Activations Density 0.083%

terms related to angles and their measurements

No Comments

No Known Activations