INDEX

Explanations

terms related to scientific concepts, particularly in physics and chemistry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ogne

-0.16

åĭ

-0.16

ubi

-0.15

obao

-0.15

erness

-0.15

HL

-0.15

quan

-0.15

dog

-0.15

 dogs

-0.14

osed

-0.14

POSITIVE LOGITS

 elastic

0.23

 scattering

0.22

 Elastic

0.20

Sc

0.19

elastic

0.18

sc

0.18

 reactions

0.17

 Scatter

0.17

reaction

0.16

sc

0.16

Activations Density 0.016%

terms related to scientific concepts, particularly in physics and chemistry

No Comments

No Known Activations