INDEX

Explanations

or

np_max-act · gemini-2.0-flash

The neuron activates on qualifiers signaling minimal or absent effect—e.g. phrases like “little or no.”

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

 global

-0.07

,
↵

-0.07

 Cavs

-0.07

{"

-0.07

िच

-0.06

 *
↵

-0.06

cellent

-0.06

 evacuation

-0.06

 фор

-0.06

 Dreams

-0.06

POSITIVE LOGITS

除

0.07

idf

0.07

この

0.06

 Bukkit

0.06

 Swedish

0.06

reff

0.06

 ViewData

0.06

noho

0.06

 Famil

0.06

.if

0.06

Activations Density 0.007%

or

The neuron activates on qualifiers signaling minimal or absent effect—e.g. phrases like “little or no.”

No Comments

No Known Activations