INDEX

Explanations

terms and phrases related to definitions and interpretations in a legal or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

.Toolkit

-0.19

aida

-0.17

anian

-0.16

yen

-0.14

iras

-0.14

bourg

-0.14

aub

-0.14

tributes

-0.14

esters

-0.13

olie

-0.13

POSITIVE LOGITS

 indicate

0.27

 indicates

0.25

 indicating

0.25

è¡¨ç¤º

0.23

 indic

0.23

 indica

0.22

 reflect

0.21

 describe

0.21

 indication

0.21

 represent

0.21

Activations Density 0.191%

terms and phrases related to definitions and interpretations in a legal or technical context

No Comments

No Known Activations