INDEX

Explanations

technical or numerical references in data-related contexts

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

eczy

-0.15

Â¹

-0.14

fony

-0.14

?,?,?,?,

-0.14

.Serve

-0.14

 bÃ²

-0.14

Äģn

-0.14

adol

-0.13

erland

-0.13

-Ð²

-0.13

POSITIVE LOGITS

0.52

 three

0.38

 third

0.36

-three

0.35

 Three

0.35

ä¸ī

0.34

 Third

0.34

Û³

0.33

ï¼ĵ

0.33

 ä¸ī

0.33

Activations Density 0.088%

technical or numerical references in data-related contexts

No Comments

No Known Activations