INDEX

Explanations

technical terms related to machine learning and feature extraction in data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

âķĲâķĲ

-0.15

ieri

-0.15

 SÄ±n

-0.14

erton

-0.14

teÅŁ

-0.14

izo

-0.14

heim

-0.14

 Knights

-0.14

alla

-0.14

Ð»Ð°Ð´Ð°

-0.14

POSITIVE LOGITS

 representation

0.21

 representations

0.21

features

0.19

 features

0.19

Mah

0.19

 feature

0.19

 vectors

0.18

 Representation

0.18

representation

0.18

Representation

0.18

Activations Density 0.024%

technical terms related to machine learning and feature extraction in data analysis

No Comments

No Known Activations