INDEX

Explanations

variations of the word "idea" and concepts surrounding it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ascade

-0.15

itsu

-0.15

isters

-0.14

orted

-0.14

ucer

-0.13

/mol

-0.13

esion

-0.13

fon

-0.13

ibly

-0.13

cin

-0.13

POSITIVE LOGITS

 itself

0.17

ÑĢÐ°ÑģÑĤÐ°

0.17

inch

0.15

ØªÙĬÙĨ

0.15

niest

0.15

 Î±ÏħÏĦÎ®

0.15

urb

0.15

.fm

0.14

 Pros

0.14

SetColor

0.14

Activations Density 0.182%

variations of the word "idea" and concepts surrounding it

No Comments

No Known Activations