INDEX

Explanations

node

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_ci

-0.06

 craft

-0.06

 calibration

-0.06

 smrti

-0.06

 empirical

-0.06

 suits

-0.06

%%%%

-0.06

WhatsApp

-0.06

 cleared

-0.06

 зберіг

-0.05

POSITIVE LOGITS

Node

0.09

node

0.09

 Nodes

0.09

 node

0.09

 Node

0.09

getNode

0.09

Nodes

0.09

_nodes

0.08

nod

0.08

 nodeId

0.08

Activations Density 0.023%

node

No Comments

No Known Activations