INDEX

Explanations

key phrases and concepts related to change and classification

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

again

-0.19

 again

-0.17

 Again

-0.16

isy

-0.16

idan

-0.15

orthy

-0.15

 Ment

-0.15

Again

-0.14

 Unless

-0.14

AGAIN

-0.14

POSITIVE LOGITS

 during

0.53

during

0.50

 durante

0.47

 During

0.44

During

0.43

 wÃ¤hrend

0.38

 given

0.34

 bÄĽhem

0.33

 tijd

0.32

given

0.30

Activations Density 0.006%

key phrases and concepts related to change and classification

No Comments

No Known Activations