INDEX

Explanations

instances of the word "using" along with the context of technical or programming frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

esk

-0.15

VectorXd

-0.15

´Ī

-0.15

ply

-0.14

indow

-0.14

InMillis

-0.14

riers

-0.13

/fixtures

-0.13

agma

-0.13

POSITIVE LOGITS

 Battles

0.18

 bitir

0.17

 commerc

0.16

anke

0.15

 Essen

0.15

iglia

0.15

 Microsoft

0.15

dot

0.15

 itemprop

0.15

ãĥ³ãĥ

0.15

Activations Density 0.013%

instances of the word "using" along with the context of technical or programming frameworks

No Comments

No Known Activations