INDEX

Explanations

references to historical landmarks and architecture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

rug

-0.15

 moon

-0.15

AccessType

-0.15

iglia

-0.14

pl

-0.14

 working

-0.14

VRT

-0.14

bub

-0.14

ENO

-0.14

 habit

-0.14

POSITIVE LOGITS

pets

0.15

 kvinder

0.15

 iconName

0.15

esa

0.14

ÏģÎ¯

0.14

Î¯Î´

0.14

}}],↵

0.14

ãĥ¼ãĥķ

0.14

impse

0.14

ethereum

0.14

Activations Density 0.049%

references to historical landmarks and architecture

No Comments

No Known Activations