INDEX

Explanations

more information

np_max-act · gemini-2.0-flash

The neuron fires on phrases introducing further‐reading or documentation references (e.g. “for more information on …,” “see our … documentation,” etc.).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_workers

-0.07

portal

-0.07

ящих

-0.07

、や

-0.07

 있는

-0.07

always

-0.06

-yellow

-0.06

各

-0.06

人的

-0.06

 Tell

-0.06

POSITIVE LOGITS

茂

0.07

 Appeals

0.06

 bats

0.06

pies

0.06

*dx

0.06

_Form

0.06

 padx

0.06

 асп

0.06

 liability

0.05

mons

0.05

Activations Density 0.057%

more information

The neuron fires on phrases introducing further‐reading or documentation references (e.g. “for more information on …,” “see our … documentation,” etc.).

No Comments

No Known Activations