INDEX

Explanations

Code/Enumeration

np_max-act · gemini-2.0-flash

The neuron fires on ordinal words (e.g. “first,” “second,” “third,” “fourth,” etc.).

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

 nutritious

-0.06

ira

-0.06

 contrary

-0.06

uo

-0.06

tuy

-0.06

 politics

-0.06

uye

-0.06

 future

-0.06

 Layout

-0.06

 któ

-0.06

POSITIVE LOGITS

 трав

0.07

tingham

0.07

(fabs

0.06

Ан

0.06

EXPR

0.06

constexpr

0.06

 Trou

0.06

.assertIn

0.06

_join

0.06

(test

0.06

Activations Density 0.217%

Code/Enumeration

The neuron fires on ordinal words (e.g. “first,” “second,” “third,” “fourth,” etc.).

No Comments

No Known Activations