INDEX

Explanations

mentions of awards and recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 nÃło

-0.15

 Affero

-0.15

Ð½Ð¸ÑĨÑı

-0.15

 Ã´

-0.15

Ãºc

-0.15

orda

-0.14

"name

-0.14

)o

-0.14

rech

-0.14

etto

-0.14

POSITIVE LOGITS

 coveted

0.16

Obs

0.16

obs

0.15

ildo

0.14

coni

0.14

$_

0.14

kovÃ©

0.14

undry

0.14

ried

0.14

Activations Density 0.056%

mentions of awards and recognitions

No Comments

No Known Activations