INDEX

Explanations

structural elements and formatting in documents

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

lets

-0.17

ses

-0.17

otions

-0.15

onse

-0.14

ivre

-0.14

ercial

-0.14

abox

-0.14

.ColumnHeader

-0.14

avery

-0.14

_iterator

-0.13

POSITIVE LOGITS

oulos

0.15

oon

0.15

Doe

0.14

ä½

0.14

ÑĥÑĤÑĮ

0.14

 Russell

0.14

oldt

0.14

 quart

0.14

 Lamb

0.13

roup

0.13

Activations Density 3.519%

structural elements and formatting in documents

No Comments

No Known Activations