INDEX

Explanations

verb

np_max-act · gemini-2.0-flash

The neuron detects mentions of “verb” or “verbs,” especially in grammar‐list contexts.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

elements related to language learning and grammar structures.

oai_token-act-pair · gpt-4o-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

 данны

-0.07

istribute

-0.07

closure

-0.06

owanie

-0.06

oh

-0.06

eload

-0.06

_elems

-0.06

Mix

-0.06

 Anat

-0.06

 patriotism

-0.06

POSITIVE LOGITS

 verbs

0.11

 verb

0.10

Verb

0.08

 Verb

0.07

+b

0.07

 arbe

0.07

 wrists

0.07

=_('

0.06

TV

0.06

<Action

0.06

Activations Density 0.006%

verb

The neuron detects mentions of “verb” or “verbs,” especially in grammar‐list contexts.

elements related to language learning and grammar structures.

No Comments

No Known Activations

verb

The neuron detects mentions of “verb” or “verbs,” especially in grammar‐list contexts.

elements related to language learning and grammar structures.

No Comments

No Known Activations