INDEX

Explanations

instances of the word "it," particularly in contexts indicating experiences or sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ustr

-0.16

stu

-0.15

uum

-0.15

upp

-0.14

uzu

-0.14

stoff

-0.13

IVO

-0.13

 gilt

-0.13

 reasonable

-0.13

POSITIVE LOGITS

 felt

0.23

 feels

0.21

 feel

0.20

 truly

0.19

anagan

0.17

feel

0.16

 Feel

0.16

felt

0.16

Feel

0.15

 honestly

0.15

Activations Density 0.078%

instances of the word "it," particularly in contexts indicating experiences or sentiments

No Comments

No Known Activations