INDEX

Explanations

programming-related keywords and declarations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

plex

-0.17

automation

-0.15

monton

-0.14

igit

-0.14

igi

-0.14

ÑĥÐ»Ñı

-0.14

atas

-0.14

Mui

-0.13

rud

-0.13

 èµ¤

-0.13

POSITIVE LOGITS

AME

0.15

veau

0.14

ÏĦÎ¹Ïĥ

0.14

APSHOT

0.14

 tipping

0.14

ERG

0.14

ftype

0.14

RuntimeObject

0.14

º

0.14

duto

0.14

Activations Density 0.009%

programming-related keywords and declarations

No Comments

No Known Activations