INDEX

Explanations

instances of dividing content into parts or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ÑĢÐ°Ð²Ð¸Ð»ÑĮ

-0.15

Kho

-0.14

ÐºÑĥÐ»

-0.14

ãĥŁãĥ¥

-0.14

muz

-0.14

Ø®Ø¨

-0.14

iggs

-0.13

FK

-0.13

 umbrella

-0.13

POSITIVE LOGITS

lage

0.17

aven

0.15

amt

0.15

okie

0.15

enÃ§a

0.14

à¸¢à¸ĩ

0.14

Ïį

0.13

TRS

0.13

 Counsel

0.13

arts

0.13

Activations Density 0.039%

instances of dividing content into parts or categories

No Comments

No Known Activations