INDEX

Explanations

references to scientific principles or formulas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

heimer

-0.14

âĺħ

-0.14

 Battles

-0.13

 hash

-0.13

 Scre

-0.13

pear

-0.13

 Towers

-0.13

POSITIVE LOGITS

uft

0.15

ä»²

0.15

¸ı

0.14

ikip

0.14

Ĵ

0.13

 multiplied

0.13

avigate

0.13

loÅ¾

0.13

.mozilla

0.13

/kubernetes

0.13

Activations Density 0.000%

references to scientific principles or formulas

No Comments

No Known Activations