INDEX

Explanations

judgment

np_max-act · gemini-2.0-flash

The neuron specifically fires on the word “judgment,” marking instances where the text discusses making decisions or using one’s judgment.

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

	UObject

-0.07

_GenericClass

-0.07

scp

-0.06

.price

-0.06

Quit

-0.06

.JsonIgnore

-0.06

民

-0.06

 afford

-0.06

(UnityEngine

-0.06

<LM

-0.06

POSITIVE LOGITS

 judgment

0.08

 judgments

0.08

 judgement

0.07

 Gard

0.06

 Γεω

0.06

 conviction

0.06

 knowing

0.06

 Luck

0.06

РА

0.06

 карт

0.06

Activations Density 0.007%

judgment

The neuron specifically fires on the word “judgment,” marking instances where the text discusses making decisions or using one’s judgment.

No Comments

No Known Activations