INDEX

Explanations

phrases indicating scientific measurements or significant concepts in a research context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ð°Ð»Ð¾Ð¼

-0.17

 insurance

-0.17

insurance

-0.16

OffsetTable

-0.15

idenav

-0.15

 cÃ¢n

-0.15

 Insurance

-0.14

Insurance

-0.14

EDI

-0.13

ongan

-0.13

POSITIVE LOGITS

 neutr

0.38

 sterile

0.30

 oscill

0.28

Osc

0.24

mu

0.24

 reactor

0.23

antine

0.22

 Î½

0.22

 solar

0.21

nu

0.21

Activations Density 0.001%

phrases indicating scientific measurements or significant concepts in a research context

No Comments

No Known Activations