INDEX

Explanations

Software translation snippets

np_max-act · gemini-2.0-flash

The neuron fires strongly on short, English-language UI action labels (e.g. “Load…,” “Save…,” “Grab…”) inside resource or string definitions.

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

_NPC

-0.07

.Comparator

-0.07

.Enum

-0.07

sched

-0.06

 itch

-0.06

implemented

-0.06

IDENT

-0.06

_deleted

-0.06

Yet

-0.06

 которым

-0.06

POSITIVE LOGITS

 Yatırım

0.07

 lateral

0.07

otation

0.07

 occupants

0.06

erville

0.06

airro

0.06

 Lindsey

0.06

 hastalık

0.06

ơi

0.06

 kaynağı

0.06

Activations Density 0.015%

Software translation snippets

The neuron fires strongly on short, English-language UI action labels (e.g. “Load…,” “Save…,” “Grab…”) inside resource or string definitions.

No Comments

No Known Activations