INDEX

Explanations

instances of the word "introduction" and its variations, indicating a focus on the concept or act of introducing something or someone

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

åĻ¨

-0.17

inders

-0.15

fully

-0.15

ACE

-0.15

opal

-0.14

 cosa

-0.14

/she

-0.13

chu

-0.13

uality

-0.13

POSITIVE LOGITS

ductory

0.33

duct

0.20

 Into

0.20

Into

0.19

 into

0.19

/export

0.18

ÈĽi

0.18

/rem

0.18

into

0.17

 INTO

0.17

Activations Density 0.024%

instances of the word "introduction" and its variations, indicating a focus on the concept or act of introducing something or someone

No Comments

No Known Activations