INDEX

Explanations

references to figures and tables in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

.portal

-0.16

boa

-0.15

age

-0.15

.ScrollBars

-0.14

annon

-0.14

amon

-0.14

à¹īà¸Ńà¸Ļ

-0.14

ÑģÑĤÐ°Ð½

-0.14

amine

-0.13

snap

-0.13

POSITIVE LOGITS

.scalablytyped

0.16

PropertyValue

0.16

 Beled

0.15

coli

0.14

raquo

0.14

otec

0.13

pto

0.13

arella

0.13

wright

0.13

 astronom

0.13

Activations Density 0.069%

references to figures and tables in a document

No Comments

No Known Activations