INDEX

Explanations

academic and scientific terms related to experimental results and machine learning models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

adders

-0.15

uden

-0.14

_QMARK

-0.14

bbing

-0.13

 anale

-0.13

.ribbon

-0.13

 UIAlert

-0.13

 Programme

-0.13

ograd

-0.12

 iParam

-0.12

POSITIVE LOGITS

 feature

0.29

 Feature

0.28

 classifier

0.26

 classifiers

0.26

 features

0.24

Feature

0.23

 classification

0.23

feature

0.23

 Features

0.23

-feature

0.22

Activations Density 0.021%

academic and scientific terms related to experimental results and machine learning models

No Comments

No Known Activations