INDEX

Explanations

Phone companies

np_max-act · gemini-2.0-flash

The neuron fires on mentions of major U.S. wireless carriers’ names (e.g. “AT&T” and “Verizon”).

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

OME

-0.06

 poder

-0.06

aines

-0.06

Keep

-0.06

 이것

-0.06

 xbox

-0.06

ible

-0.06

اطر

-0.06

 注意

-0.06

 آخر

-0.06

POSITIVE LOGITS

subscriber

0.07

 klíč

0.07

ForeColor

0.06

 boutique

0.06

riot

0.06

.ImageIcon

0.06

 Telecom

0.06

 martial

0.06

/sys

0.06

 ambient

0.06

Activations Density 0.011%

Phone companies

The neuron fires on mentions of major U.S. wireless carriers’ names (e.g. “AT&T” and “Verizon”).

No Comments

No Known Activations