INDEX

Explanations

2

np_max-act · gemini-2.0-flash

This neuron activates on tokens involved in exponent notation (e.g., the caret “^” and the following exponent digits).

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

Auto

-0.06

Csv

-0.06

 طور

-0.06

 kotlin

-0.06

ota

-0.06

_paths

-0.06

リス

-0.06

стер

-0.06

middlewares

-0.06

 پل

-0.06

POSITIVE LOGITS

่น

0.07

])));↵

0.07

.Values

0.07

])),

0.07

)/(

0.07

_seat

0.06

cular

0.06

 stř

0.06

 Pixels

0.06

σου

0.06

Activations Density 0.015%

2

This neuron activates on tokens involved in exponent notation (e.g., the caret “^” and the following exponent digits).

No Comments

No Known Activations