INDEX

Explanations

terminology related to scientific recognition or classification

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

ares

-0.19

fts

-0.15

rana

-0.14

orgh

-0.14

GLOSS

-0.14

azio

-0.14

olina

-0.14

ãĥ¼ãĥĬ

-0.13

codes

-0.13

POSITIVE LOGITS

 simply

0.28

 Simply

0.23

Simply

0.23

 commonly

0.21

0.20

 inform

0.19

 popular

0.19

ä¿Ĺ

0.19

 simplement

0.18

 affection

0.17

Activations Density 0.025%

terminology related to scientific recognition or classification

No Comments

No Known Activations