INDEX

Explanations

proper nouns, specifically personal names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

xFD

-0.16

Úĺ

-0.15

edom

-0.15

elerik

-0.14

 kÃ¼r

-0.14

ÑĤÐ¸Ðº

-0.14

.openConnection

-0.14

anut

-0.14

ums

-0.14

_fd

-0.14

POSITIVE LOGITS

rega

0.16

weeney

0.15

atan

0.15

arrera

0.15

ombo

0.14

linger

0.14

omon

0.14

regar

0.14

 Ð¾ÐºÑĢÐ°

0.14

oger

0.14

Activations Density 0.011%

proper nouns, specifically personal names and locations

No Comments

No Known Activations