INDEX

Explanations

terms related to the classification and characteristics of organisms or biological entities

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

àµį

-0.18

ivate

-0.17

iven

-0.15

imento

-0.15

infeld

-0.15

apon

-0.15

iment

-0.14

/stdc

-0.14

 Ekim

-0.14

Ø§ÙĨ

-0.14

POSITIVE LOGITS

orph

0.27

orphism

0.22

orphic

0.22

ycin

0.21

atically

0.20

olecular

0.20

etric

0.18

bed

0.18

ptive

0.18

otive

0.17

Activations Density 0.103%

terms related to the classification and characteristics of organisms or biological entities

No Comments

No Known Activations