INDEX

Explanations

words that describe conditions or states related to health and well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ÐµÐ²Ð°

-0.18

eor

-0.17

elo

-0.17

etur

-0.16

sei

-0.16

akov

-0.15

aka

-0.15

esk

-0.15

enda

-0.15

nop

-0.14

POSITIVE LOGITS

ÑĽ

0.30

Ñ

0.24

Äĩe

0.24

Ñĺ

0.22

ÑĴ

0.22

Äĩi

0.22

Ð¾

0.21

Ð¾ÑĨÐ¸

0.20

Ð¾Ð½Ð¸

0.19

Activations Density 0.006%

words that describe conditions or states related to health and well-being

No Comments

No Known Activations