INDEX

Explanations

answers

np_max-act · gemini-2.0-flash

This neuron activates on floating-point numeric literals (decimal numbers).

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

 guards

-0.07

تی

-0.07

vertime

-0.06

iation

-0.06

.assertNotNull

-0.06

tox

-0.06

 marginLeft

-0.06

allah

-0.06

 turns

-0.06

 transient

-0.06

POSITIVE LOGITS

_HAVE

0.07

Suit

0.07

_VE

0.07

^^

0.06

Vectorizer

0.06

(elem

0.06

 çıkar

0.06

 synerg

0.06

(set

0.06

Activations Density 0.071%

answers

This neuron activates on floating-point numeric literals (decimal numbers).

No Comments

No Known Activations