INDEX

Explanations

references to locations or areas within various contexts

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

 Magick

-0.16

_DAC

-0.15

izo

-0.15

ourd

-0.14

VT

-0.14

stp

-0.14

irates

-0.14

 FactoryBot

-0.14

annon

-0.14

urse

-0.14

POSITIVE LOGITS

Äįen

0.14

 Fang

0.14

stderr

0.14

},'

0.13

çİĦ

0.13

âĹİ

0.13

¢åįķ

0.13

ÏģÎ¿Ïį

0.13

)((((

0.13

ãĥ³ãĥĶ

0.13

Activations Density 0.288%

references to locations or areas within various contexts

No Comments

No Known Activations