INDEX

Explanations

attributes and specifications related to products, particularly in retail contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ins

-0.18

 Brad

-0.16

 Hour

-0.15

yan

-0.15

aff

-0.15

 Pound

-0.14

zd

-0.14

Å¡ka

-0.14

 North

-0.14

POSITIVE LOGITS

entialAction

0.17

anford

0.17

oldemort

0.16

ÙħÙĬÙħ

0.16

avin

0.15

.scalablytyped

0.15

ä¸įäºĨ

0.15

iVar

0.15

@nate

0.15

uÄį

0.15

Activations Density 0.067%

attributes and specifications related to products, particularly in retail contexts

No Comments

No Known Activations