INDEX

Explanations

references to publishers and publication details in texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

sez

-0.16

acro

-0.15

dit

-0.15

/topics

-0.14

ones

-0.14

cents

-0.14

 Lair

-0.14

inks

-0.14

elle

-0.14

ssue

-0.14

POSITIVE LOGITS

distributed

0.18

uzzi

0.17

ãĥ³ãĥĸ

0.17

 ISBN

0.17

 distrib

0.16

ãĤ¿ãĥ«

0.16

cop

0.16

udad

0.15

icers

0.15

DAL

0.15

Activations Density 0.072%

references to publishers and publication details in texts

No Comments

No Known Activations