INDEX

Explanations

mathematical structures and notations related to algebraic categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

vrier

-0.20

pite

-0.18

erten

-0.17

gettext

-0.17

onen

-0.17

tron

-0.16

 Fleming

-0.16

ÙĨÙħ

-0.16

ichel

-0.16

criptors

-0.15

POSITIVE LOGITS

ham

0.15

spl

0.14

emb

0.14

ham

0.14

chr

0.14

Ga

0.14

beh

0.13

SA

0.13

ev

0.13

Activations Density 0.024%

mathematical structures and notations related to algebraic categories

No Comments

No Known Activations