INDEX

Explanations

future tense verbs and phrases indicating intention or capability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

uien

-0.15

 themselves

-0.15

çĽĽ

-0.15

Î¹Î»Î¿

-0.15

ibal

-0.14

eso

-0.14

icus

-0.14

 bothers

-0.14

ð

-0.14

 bothering

-0.14

POSITIVE LOGITS

 notice

0.36

 find

0.29

notice

0.27

 Notice

0.27

Notice

0.26

 notices

0.25

 want

0.25

 noticed

0.24

 hear

0.23

 note

0.22

Activations Density 0.069%

future tense verbs and phrases indicating intention or capability

No Comments

No Known Activations