INDEX

Explanations

mathematical terms and symbols in equations

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

rive

-0.18

 Tonight

-0.16

Cob

-0.16

obble

-0.15

utto

-0.15

Tonight

-0.15

OAD

-0.14

sched

-0.14

elik

-0.14

vap

-0.14

POSITIVE LOGITS

div

0.23

DIV

0.19

-div

0.19

div

0.18

 divergence

0.17

 grad

0.16

Duy

0.16

(div

0.16

(grad

0.16

 Malone

0.15

Activations Density 0.295%

mathematical terms and symbols in equations

No Comments

No Known Activations