INDEX

Explanations

commands and instructions related to programming, specifically for a framework or library

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

aeda

-0.19

ë¶

-0.15

pector

-0.14

ufs

-0.14

rego

-0.14

zy

-0.14

 cour

-0.14

 NDEBUG

-0.14

ettle

-0.14

apult

-0.14

POSITIVE LOGITS

isl

0.16

 dokon

0.15

åĢĻ

0.14

 Dann

0.14

ipel

0.14

Ð¸Ð½Ð¾Ð²

0.14

.twitch

0.13

itters

0.13

ONY

0.13

ahr

0.13

Activations Density 0.006%

commands and instructions related to programming, specifically for a framework or library

No Comments

No Known Activations