INDEX

Explanations

references to mathematical or scientific concepts and notations

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

-0.14

foy

-0.14

eks

-0.13

ÄĽr

-0.13

istani

-0.13

ÙĨØ§ÙĨ

-0.13

à¸¥à¸°

-0.13

 McCart

-0.13

/Library

-0.13

jumbotron

-0.13

POSITIVE LOGITS

 trough

0.20

agt

0.16

idan

0.15

 Worm

0.15

_definitions

0.15

)|(

0.14

imits

0.14

pta

0.14

AIL

0.13

enin

0.13

Activations Density 0.004%

references to mathematical or scientific concepts and notations

No Comments

No Known Activations