INDEX

Explanations

terms related to classification and functionality in various domains, including cinema, fitness, and technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.16

ë¹Į

-0.15

-0.14

Î¼Î¯

-0.13

 Hern

-0.13

apus

-0.13

iphy

-0.13

POSITIVE LOGITS

mlink

0.14

conomy

0.14

batim

0.14

é«ĺæ¸ħ

0.14

aucoup

0.14

Ì

0.13

ãĥĭãĤ¢

0.13

Ì§

0.13

æ§

0.13

å®¿

0.13

Activations Density 0.094%

terms related to classification and functionality in various domains, including cinema, fitness, and technical specifications

No Comments

No Known Activations