INDEX

Explanations

numeric values, particularly in the format of addresses and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

bum

-0.16

alk

-0.15

UCE

-0.15

 Morrow

-0.14

Dag

-0.14

 trÃł

-0.14

uta

-0.14

auer

-0.13

ÑģÑĤÐ¸Ð½

-0.13

ass

-0.13

POSITIVE LOGITS

CellValue

0.15

ules

0.15

_Abstract

0.15

alon

0.14

/datatables

0.14

 ancor

0.14

Affected

0.14

gable

0.14

 Pitch

0.14

ãİ

0.14

Activations Density 0.042%

numeric values, particularly in the format of addresses and measurements

No Comments

No Known Activations