INDEX

Explanations

discover

np_max-act · gemini-2.0-flash

This neuron fires on occurrences of the verb “discover” (and its inflected forms).

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

 metavar

-0.07

_att

-0.07

 maxValue

-0.07

rtl

-0.06

Bet

-0.06

 utmost

-0.06

 bent

-0.06

 hotline

-0.06

 Terrain

-0.06

POSITIVE LOGITS

 discovered

0.14

 discovery

0.13

 Discovery

0.12

 discover

0.12

 Discover

0.10

discover

0.10

 discovers

0.10

 discovering

0.10

Discover

0.09

 discoveries

0.08

Activations Density 0.020%

discover

This neuron fires on occurrences of the verb “discover” (and its inflected forms).

No Comments

No Known Activations