INDEX

Explanations

terms related to oxidation and antioxidants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ï¸

-0.16

bach

-0.15

fik

-0.15

 Vict

-0.15

Ont

-0.14

ISTRY

-0.14

TINGS

-0.14

ELLOW

-0.14

icast

-0.14

POSITIVE LOGITS

idental

0.17

ÐºÐ¾Ð¿

0.16

alic

0.15

íĢ

0.15

kowski

0.15

tober

0.15

ides

0.14

ford

0.14

enou

0.14

ses

0.14

Activations Density 0.014%

terms related to oxidation and antioxidants

No Comments

No Known Activations