INDEX

Explanations

code-related terms 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

à¤¤à¤°

-0.16

leurs

-0.15

ÑĢÑĥÑĩ

-0.15

á»¯u

-0.15

esan

-0.14

immutable

-0.14

à¸µà¸¢à¸ļ

-0.14

eced

-0.14

 attendance

-0.14

imest

-0.14

POSITIVE LOGITS

.run

0.21

run

0.20

-runner

0.20

run

0.20

 Runner

0.19

Runner

0.19

 runner

0.18

è¿Ĳè¡Į

0.18

ran

0.18

Run

0.18

Activations Density 0.304%

code-related terms and structures

No Comments

No Known Activations