INDEX

Explanations

references to the word "Lou" 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 @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

baum

-0.18

ria

-0.16

ni

-0.15

 typeof

-0.14

apat

-0.14

Ð¾ÑģÑĤÐ°Ð²

-0.14

senal

-0.13

atis

-0.13

rade

-0.13

 preferably

-0.13

POSITIVE LOGITS

ise

0.28

vre

0.28

isa

0.27

nger

0.23

ie

0.21

lou

0.21

Lou

0.21

igi

0.21

loud

0.21

verture

0.21

Activations Density 0.004%

references to the word "Lou" in various contexts

No Comments

No Known Activations