INDEX

Explanations

iber/deliber

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of the root “deliber” (e.g. in words like deliberate, deliberative, deliberation).

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

 antioxidant

-0.07

 ranked

-0.06

Owner

-0.06

NG

-0.06

 accessed

-0.06

XXXXXXXX

-0.06

 pricey

-0.06

 unary

-0.06

uckets

-0.06

	free

-0.06

POSITIVE LOGITS

 deliberate

0.11

 deliberately

0.10

 deliber

0.10

 действ

0.08

per

0.07

lbl

0.07

 excessive

0.07

 probable

0.07

による

0.07

 Camel

0.07

Activations Density 0.002%

iber/deliber

This neuron activates on occurrences of the root “deliber” (e.g. in words like deliberate, deliberative, deliberation).

No Comments

No Known Activations