INDEX

Explanations

code-related terminology and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

.Transactional

-0.17

ighton

-0.16

_NC

-0.16

 Broad

-0.16

emachine

-0.15

utenberg

-0.15

anguard

-0.15

âĿ

-0.15

Assembly

-0.14

Broad

-0.14

POSITIVE LOGITS

 Ø§ÙĦØ¨Ø¯

0.16

 Howell

0.15

Jak

0.15

 Nimbus

0.14

Ø³ÙĪØ¨

0.14

Ã¤ft

0.14

 laps

0.14

èĵ

0.14

 Willis

0.14

oval

0.14

Activations Density 0.003%

code-related terminology and structures

No Comments

No Known Activations