INDEX

Explanations

phrases related to data analysis and calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ermal

-0.15

èĭĹ

-0.15

çĬ¬

-0.14

 Hudson

-0.14

rement

-0.14

Disposable

-0.14

_TRANSFER

-0.13

 plate

-0.13

mites

-0.13

 glass

-0.13

POSITIVE LOGITS

 Measures

0.31

 measures

0.30

 measure

0.27

 slic

0.27

MD

0.26

 cube

0.25

 Measure

0.25

 dimension

0.24

Cube

0.23

 Cube

0.23

Activations Density 0.010%

phrases related to data analysis and calculations

No Comments

No Known Activations