INDEX

Explanations

training

np_max-act · gemini-2.0-flash

the neuron activates on mentions of the model’s training (e.g. “trained,” “training,” or “data” in that context).

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

SF

-0.06

codile

-0.06

 witnessed

-0.06

user

-0.06

ιαν

-0.06

@d

-0.06

space

-0.06

เร

-0.06

埋

-0.06

POSITIVE LOGITS

.getCode

0.07

format

0.07

.='

0.07

卫

0.06

 doPost

0.06

{}_

0.06

Quy

0.06

 Nhà

0.06

音

0.06

ROLS

0.06

Activations Density 0.015%

training

the neuron activates on mentions of the model’s training (e.g. “trained,” “training,” or “data” in that context).

No Comments

No Known Activations

training

the neuron activates on mentions of the model’s training (e.g. “trained,” “training,” or “data” in that context).

No Comments

No Known Activations