INDEX

Explanations

statistical data and numerical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

asl

-0.17

Č↵

-0.17

/repository

-0.15

ught

-0.14

assi

-0.14

venir

-0.13

rase

-0.13

agner

-0.13

ombat

-0.12

 compens

-0.12

POSITIVE LOGITS

 cases

0.26

cases

0.20

 patients

0.18

 Cases

0.18

Cases

0.15

 casos

0.15

 patents

0.15

.vs

0.15

 records

0.15

åħ¶ä¸Ń

0.15

Activations Density 0.056%

statistical data and numerical information

No Comments

No Known Activations