INDEX

Explanations

references to sections or parts of a larger work

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

ete

-0.15

 races

-0.14

awn

-0.14

atos

-0.14

ÐµÑĤÐµ

-0.14

ISK

-0.14

et

-0.13

Ø§Ø¨Øª

-0.13

ep

-0.13

emain

-0.13

POSITIVE LOGITS

loys

0.16

appa

0.16

ums

0.16

creds

0.15

 Sands

0.15

lfw

0.15

marshall

0.15

vfs

0.15

PTH

0.14

æ¸Ī

0.14

Activations Density 0.049%

references to sections or parts of a larger work

No Comments

No Known Activations