INDEX

Explanations

interrogative phrases typically found in questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

annes

-0.16

arti

-0.16

elter

-0.15

 quoi

-0.15

amm

-0.14

cano

-0.14

oca

-0.14

razier

-0.14

orie

-0.14

POSITIVE LOGITS

 advice

0.24

 Advice

0.20

Advice

0.18

 advise

0.16

 brought

0.16

 appealed

0.15

ä½¿

0.15

pek

0.15

onet

0.14

 prep

0.14

Activations Density 0.044%

interrogative phrases typically found in questions

No Comments

No Known Activations