INDEX

Explanations

instances of numerical data or statistical mentions within texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

/from

-0.18

ero

-0.16

ccion

-0.15

Äįek

-0.15

positor

-0.15

Ð´Ð°

-0.14

ducted

-0.14

duct

-0.14

erland

-0.14

curring

-0.14

POSITIVE LOGITS

 present

0.22

 presente

0.18

å¿ĥ

0.17

SAME

0.17

testing

0.16

 last

0.16

 stake

0.16

 times

0.16

woord

0.15

risk

0.15

Activations Density 0.062%

instances of numerical data or statistical mentions within texts

No Comments

No Known Activations