INDEX

Explanations

references to geographical locations and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

illac

-0.20

pour

-0.16

ÎŃÏģÎ³

-0.16

ano

-0.15

ovan

-0.14

å¹¹ç·ļ

-0.14

SCI

-0.14

loon

-0.14

unused

-0.14

NotFound

-0.13

POSITIVE LOGITS

DOI

0.17

ImageContext

0.15

0.14

ä¸ģ

0.14

Facade

0.14

 Tiny

0.13

aje

0.13

isÃŃ

0.13

strup

0.13

ets

0.13

Activations Density 0.151%

references to geographical locations and their characteristics

No Comments

No Known Activations