INDEX

Explanations

contact information for professionals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 founder

-0.18

amedi

-0.17

 founders

-0.17

 Founder

-0.16

äºĭåĭĻ

-0.16

Founder

-0.15

.googlecode

-0.15

vÅ¯

-0.15

ibi

-0.15

irq

-0.14

POSITIVE LOGITS

 teams

0.16

 blogs

0.15

gard

0.14

 Barcl

0.14

ora

0.14

 internal

0.14

ese

0.14

quil

0.13

 Division

0.13

ded

0.13

Activations Density 0.172%

contact information for professionals and organizations

No Comments

No Known Activations