INDEX

Explanations

references to descriptive features and characteristics in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

å±

-0.17

Ø§Ø«

-0.16

PN

-0.15

rolls

-0.15

agrid

-0.14

ÑĢÐ¸Ðº

-0.14

Klo

-0.14

pn

-0.14

 Kale

-0.14

ãĤ«ãĥ¼

-0.14

POSITIVE LOGITS

ipay

0.15

æŃ

0.14

sted

0.13

affer

0.13

sitemap

0.13

lodash

0.13

eric

0.13

uzey

0.13

esch

0.13

ilder

0.13

Activations Density 0.905%

references to descriptive features and characteristics in various contexts

No Comments

No Known Activations