INDEX

Explanations

programming-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

wind

-0.17

.skip

-0.15

ud

-0.15

 stub

-0.15

kel

-0.14

æİ¢

-0.14

CharCode

-0.14

dot

-0.14

 perpendicular

-0.14

_DLL

-0.14

POSITIVE LOGITS

 boundaries

0.19

 QRect

0.17

:CGRect

0.17

size

0.16

éĿ¢ç§¯

0.16

 boundary

0.16

nested

0.15

 rectangle

0.15

CGRect

0.15

åĽ²

0.15

Activations Density 0.127%

programming-related content

No Comments

No Known Activations