INDEX

Explanations

ideas

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 triệu

-0.07

-terrorism

-0.07

jsonwebtoken

-0.07

 використ

-0.07

.SuppressLint

-0.06

 offsetof

-0.06

公开

-0.06

customer

-0.06

 канди

-0.06

 здійснення

-0.06

POSITIVE LOGITS

 ideas

0.10

 Ideas

0.09

 thought

0.07

 Ideal

0.07

PERTY

0.07

 Thought

0.07

 disappearing

0.07

 Sophia

0.07

 Idea

0.07

Thought

0.07

Activations Density 0.020%

ideas

No Comments

No Known Activations

ideas

No Comments

No Known Activations