INDEX

Explanations

coding-related keywords and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

elves

-0.17

 useClass

-0.15

rlen

-0.14

Ā

-0.13

ago

-0.13

paces

-0.13

 \↵

-0.13

 Duch

-0.13

odings

-0.12

à¤¦à¤®

-0.12

POSITIVE LOGITS

erli

0.16

isos

0.15

¹Ħ

0.14

assin

0.13

.SuspendLayout

0.13

iston

0.13

 Ð²ÐµÐ´ÑĮ

0.13

avir

0.13

engin

0.13

overe

0.12

Activations Density 1.030%

coding-related keywords and functions

No Comments

No Known Activations