INDEX

Explanations

punctuation marks, specifically commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

oker

-0.17

wyn

-0.16

endale

-0.16

bole

-0.15

addle

-0.14

cott

-0.14

IntArray

-0.14

_ONCE

-0.14

intel

-0.14

 millet

-0.14

POSITIVE LOGITS

cih

0.17

ateria

0.17

0.16

oz

0.15

cco

0.15

ìłķìĿ´

0.14

 ApiController

0.14

 Gest

0.14

ovÄĽ

0.14

essional

0.14

Activations Density 0.003%

punctuation marks, specifically commas

No Comments

No Known Activations