INDEX

Explanations

mentions of the letter 'R' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ange

-0.20

vat

-0.17

adio

-0.17

ails

-0.17

ries

-0.16

oller

-0.16

adius

-0.16

ock

-0.16

ank

-0.16

anch

-0.15

POSITIVE LOGITS

alf

0.18

aul

0.17

INU

0.16

inder

0.16

afe

0.15

andal

0.15

olf

0.15

 Kelly

0.15

-rated

0.15

ylan

0.15

Activations Density 0.041%

mentions of the letter 'R' in various contexts

No Comments

No Known Activations