INDEX

Explanations

mathematical proofs and theorems related to analytical methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ypo

-0.15

ÑĥÑģÑĤ

-0.15

 benim

-0.15

ahlen

-0.15

áº¿

-0.15

arpa

-0.14

/oct

-0.14

enco

-0.14

jest

-0.14

éĥ

-0.14

POSITIVE LOGITS

 Morrison

0.15

noch

0.15

0.14

yy

0.14

ingham

0.14

eria

0.14

uja

0.14

toc

0.14

punkt

0.14

Å¡ka

0.14

Activations Density 0.126%

mathematical proofs and theorems related to analytical methods

No Comments

No Known Activations