INDEX

Explanations

mentions of looping or repetitive concepts in programming contexts

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

onne

-0.17

 sworn

-0.15

utow

-0.15

owler

-0.15

oose

-0.15

à¤¿à¤¯à¤¤

-0.15

Mov

-0.15

aat

-0.15

ections

-0.15

cela

-0.15

POSITIVE LOGITS

ingly

0.20

sters

0.18

ed

0.18

-loop

0.17

edList

0.17

à¸Ļ

0.16

icle

0.16

edback

0.16

otron

0.16

edImage

0.16

Activations Density 0.068%

mentions of looping or repetitive concepts in programming contexts

No Comments

No Known Activations