INDEX

Explanations

elements related to coding or programming tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

isks

-0.16

uai

-0.16

acho

-0.15

Zem

-0.14

 fully

-0.14

 Fully

-0.14

creativecommons

-0.14

uhan

-0.14

æ®µ

-0.14

han

-0.14

POSITIVE LOGITS

":[{↵

0.15

 âĶľâĶĢâĶĢ

0.15

-toggler

0.15

arent

0.14

 Latter

0.14

oldt

0.14

ä¸Ģçº§

0.14

ÑģÑĮÐ¾Ð³Ð¾

0.14

ReuseIdentifier

0.14

Activations Density 0.001%

elements related to coding or programming tasks

No Comments

No Known Activations