INDEX

Explanations

keywords related to numerical data and measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

SK

-0.16

ROM

-0.15

âĶ¬

-0.15

 Pant

-0.14

SD

-0.14

arters

-0.14

SN

-0.14

 colour

-0.14

RAR

-0.14

POSITIVE LOGITS

é£

0.16

errat

0.16

unc

0.15

uplic

0.15

enco

0.15

.BLL

0.14

Ø±ÙĪØª

0.14

Ð¾ÑģÐ¾Ð±

0.14

_unc

0.14

Accessibility

0.14

Activations Density 0.006%

keywords related to numerical data and measurement

No Comments

No Known Activations