INDEX

Explanations

descriptions and parentheticals

np_max-act · gemini-2.0-flash

The neuron fires on code‐style path and filename fragments (e.g. “init”, “ansible/utils/vars.py”, import-path segments).

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

дет

-0.06

resa

-0.06

ุตบอล

-0.06

eldon

-0.06

 Maths

-0.06

 привод

-0.06

 dünyanın

-0.06

př

-0.06

�

-0.06

POSITIVE LOGITS

\Validation

0.07

 investigate

0.07

":
↵

0.06

 υπό

0.06

(mean

0.06

 corresponding

0.06

 أش

0.06

 Solve

0.06

守

0.06

خف

0.06

Activations Density 0.113%

descriptions and parentheticals

The neuron fires on code‐style path and filename fragments (e.g. “__init__”, “ansible/utils/vars.py”, import-path segments).

No Comments

No Known Activations

The neuron fires on code‐style path and filename fragments (e.g. “init”, “ansible/utils/vars.py”, import-path segments).