INDEX

Explanations

comparisons of magnitudes and effects across different contexts and subjects

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ink

-0.15

Ð»Ñı

-0.15

oice

-0.14

 enough

-0.14

asse

-0.14

createView

-0.13

Getty

-0.13

iken

-0.13

CUS

-0.13

POSITIVE LOGITS

 than

0.39

-than

0.33

than

0.31

 THAN

0.29

_than

0.29

 Than

0.28

 niÅ¼

0.27

Than

0.27

 Ã¤n

0.24

 neÅ¾

0.23

Activations Density 0.326%

comparisons of magnitudes and effects across different contexts and subjects

No Comments

No Known Activations