INDEX

Explanations

modal verbs indicating possession or experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

won

-0.16

aldi

-0.14

Ã¤nger

-0.14

haven

-0.14

uzzi

-0.14

hani

-0.14

icias

-0.14

uat

-0.13

elian

-0.13

POSITIVE LOGITS

 long

0.31

 always

0.28

always

0.26

Always

0.23

 Always

0.23

 ALWAYS

0.22

long

0.22

 historically

0.22

 tended

0.21

 traditionally

0.21

Activations Density 0.197%

modal verbs indicating possession or experience

No Comments

No Known Activations