INDEX

Explanations

numerical data and metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

jeta

-0.15

emap

-0.15

 Conway

-0.14

 Hampton

-0.14

.ng

-0.14

á»§

-0.14

bef

-0.14

ÃŃÅ¡

-0.14

lights

-0.13

 blow

-0.13

POSITIVE LOGITS

 spin

0.28

 Spin

0.27

spin

0.25

Spin

0.25

 relaxation

0.24

 nuclear

0.24

 Nuclear

0.23

 spinning

0.23

ENDOR

0.22

 spins

0.22

Activations Density 0.004%

numerical data and metrics

No Comments

No Known Activations