INDEX

Explanations

means

np_max-act · gemini-2.0-flash

This neuron detects legal‐license definition clauses, specifically the quoted term + “means” pattern (including the “Definitions” heading).

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

]["

-0.07

_NEXT

-0.07

 Chrysler

-0.07

龍

-0.06

rows

-0.06

weise

-0.06

，又

-0.06

sci

-0.06

.fromLTRB

-0.06

考

-0.06

POSITIVE LOGITS

 nationally

0.06

Animate

0.06

pressive

0.06

).*

0.06

 Governors

0.06

 dispersed

0.06

 States

0.06

 wore

0.06

————————

0.06

 saying

0.06

Activations Density 0.006%

means

This neuron detects legal‐license definition clauses, specifically the quoted term + “means” pattern (including the “Definitions” heading).

No Comments

No Known Activations