INDEX

Explanations

code syntax and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

oure

-0.17

oring

-0.15

OfClass

-0.14

="__

-0.14

RefCount

-0.14

xn

-0.14

Ã³l

-0.13

aca

-0.13

acÄ±

-0.13

Ð¼ÐµÐ½Ð¸

-0.13

POSITIVE LOGITS

rike

0.15

inu

0.15

0.14

gages

0.14

 Immutable

0.14

lesi

0.14

ibil

0.13

 magna

0.13

gebra

0.13

Activations Density 0.143%

code syntax and function definitions

No Comments

No Known Activations