INDEX

Explanations

concepts related to progress and momentum in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Walk

-0.15

ÙĤØ¨

-0.14

ario

-0.14

 backgrounds

-0.14

rient

-0.14

 requis

-0.14

 Background

-0.13

RIES

-0.13

.gdx

-0.13

.yy

-0.13

POSITIVE LOGITS

 momentum

0.49

 Momentum

0.38

omentum

0.35

 steam

0.33

steam

0.28

 traction

0.28

 acceleration

0.27

 pace

0.26

 gaining

0.24

moment

0.23

Activations Density 0.201%

concepts related to progress and momentum in various contexts

No Comments

No Known Activations