INDEX

Explanations

period

np_max-act · gemini-2.0-flash

The neuron fires on the “v . 2 . 0” license‐version tokens in MPL header comments (i.e. the floating-point license version specification).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_scope

-0.06

 walnut

-0.06

كرة

-0.06

USS

-0.06

ABCDEFGHIJKLMNOP

-0.06

 afternoon

-0.06

商品

-0.06

-To

-0.06

面

-0.06

(zip

-0.06

POSITIVE LOGITS

 knocked

0.07

 operative

0.07

 Reached

0.06

Ctr

0.06

 inicial

0.06

 STACK

0.06

 buck

0.06

 investment

0.06

Volumes

0.06

 offensive

0.06

Activations Density 0.001%

period

The neuron fires on the “v . 2 . 0” license‐version tokens in MPL header comments (i.e. the floating-point license version specification).

No Comments

No Known Activations