INDEX

Explanations

comparisons highlighting differences between various concepts or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

kontakte

-0.17

@brief

-0.16

ardless

-0.16

#ga

-0.15

gin

-0.15

Ð¸ÑģÐ»Ð¾Ð²

-0.15

hawk

-0.15

 pies

-0.14

bard

-0.14

itchens

-0.14

POSITIVE LOGITS

 what

0.17

 usual

0.17

 other

0.16

previous

0.15

other

0.15

usual

0.15

 others

0.15

era

0.15

 PackageManager

0.15

 typical

0.15

Activations Density 0.052%

comparisons highlighting differences between various concepts or items

No Comments

No Known Activations