INDEX

Explanations

references to specific paragraphs or sections in a legal or formal document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

åĳĬ

-0.15

atz

-0.15

lah

-0.14

elter

-0.14

Ø±Ø§

-0.14

wed

-0.14

 addCriterion

-0.14

 swim

-0.13

Ordinal

-0.13

 erle

-0.13

POSITIVE LOGITS

ENU

0.16

eres

0.16

 Bottom

0.15

alance

0.15

NECTION

0.14

 vlastnÃŃ

0.14

.numpy

0.14

enu

0.14

orp

0.13

ulares

0.13

Activations Density 0.022%

references to specific paragraphs or sections in a legal or formal document

No Comments

No Known Activations