INDEX

Explanations

references to national organizations or policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

unde

-0.16

elli

-0.15

noticed

-0.15

 diaper

-0.15

anio

-0.14

ì§ĢìĹŃ

-0.14

imir

-0.14

undra

-0.14

 bell

-0.14

Ãłnh

-0.14

POSITIVE LOGITS

 Assembly

0.20

-level

0.19

 Stadium

0.18

 Mour

0.17

Assembly

0.17

semble

0.17

ities

0.17

-Level

0.17

 Library

0.17

 Broad

0.17

Activations Density 0.035%

references to national organizations or policies

No Comments

No Known Activations