INDEX

Explanations

programming keywords and method declarations

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

 Slam

-0.15

ebek

-0.15

awks

-0.15

Î¯Î´Î±

-0.14

ogany

-0.14

chl

-0.14

vla

-0.14

osit

-0.14

endir

-0.14

iteur

-0.14

POSITIVE LOGITS

fold

0.15

 dÃ©cou

0.15

 JsonResult

0.14

zew

0.13

 dynam

0.13

fo

0.13

 AydÄ±n

0.13

TI

0.13

HI

0.13

Activations Density 0.021%

programming keywords and method declarations

No Comments

No Known Activations