INDEX

Explanations

phrases related to astrophysical concepts, specifically concerning stars and fusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Orbit

-0.16

Nap

-0.16

ç³»

-0.15

 magnets

-0.15

Ky

-0.15

 ÑĥÐ²

-0.14

 Dios

-0.14

istol

-0.14

è¿·

-0.14

 orient

-0.13

POSITIVE LOGITS

 dred

0.20

 burning

0.19

 conv

0.18

urning

0.17

 abund

0.17

-core

0.17

elay

0.17

/core

0.17

 Carbon

0.17

 Burning

0.17

Activations Density 0.019%

phrases related to astrophysical concepts, specifically concerning stars and fusion

No Comments

No Known Activations