INDEX

Explanations

words related to sorting or organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

enburg

-0.17

iyat

-0.15

SET

-0.14

xit

-0.14

agal

-0.14

itar

-0.14

hores

-0.14

utra

-0.14

hari

-0.14

POSITIVE LOGITS

alia

0.15

igh

0.15

cean

0.15

png

0.14

aurus

0.14

ãİ

0.14

weg

0.14

 doma

0.14

 Levy

0.14

Alf

0.13

Activations Density 0.013%

words related to sorting or organization

No Comments

No Known Activations