INDEX

Explanations

irradi

np_max-act · gemini-2.0-flash

The neuron activates on occurrences of the root “irradiat” (as in “irradiate,” “irradiation,” “irradiated,” 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 сигн

-0.06

 Logo

-0.06

elo

-0.06

Slice

-0.06

.characters

-0.06

 newSize

-0.06

.children

-0.06

 brokers

-0.06

 faces

-0.06

Seen

-0.06

POSITIVE LOGITS

 irradi

0.14

Irr

0.12

 irritated

0.09

 irrigation

0.08

RI

0.08

ri

0.08

WidthSpace

0.08

rint

0.07

 aggress

0.07

river

0.07

Activations Density 0.007%

irradi

The neuron activates on occurrences of the root “irradiat” (as in “irradiate,” “irradiation,” “irradiated,” etc.).

No Comments

No Known Activations