INDEX

Explanations

patterns of numerical data and citations within research documents

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

clave

-0.16

-0.15

hatt

-0.15

annon

-0.14

ANNER

-0.14

çµ¶

-0.14

POSITIVE LOGITS

itura

0.15

DataMember

0.15

ContentLoaded

0.14

ernals

0.14

 Eisen

0.13

âĳł

0.13

illac

0.13

_abort

0.13

uzey

0.13

Alb

0.13

Activations Density 0.073%

patterns of numerical data and citations within research documents

No Comments

No Known Activations

patterns of numerical data and citations within research documents

No Comments

No Known Activations