INDEX

Explanations

various forms of measurement and evaluation terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

fik

-0.15

Ukr

-0.15

roat

-0.14

ilyn

-0.14

neck

-0.14

sonian

-0.13

 Legends

-0.13

 legends

-0.13

moon

-0.13

rote

-0.13

POSITIVE LOGITS

Fou

0.25

 Nietzsche

0.22

De

0.21

 Gilles

0.20

 Cinema

0.20

 Madness

0.19

 determ

0.19

 plateau

0.19

 schizophren

0.19

 Diagram

0.19

Activations Density 0.010%

various forms of measurement and evaluation terminology

No Comments

No Known Activations