INDEX

Explanations

Dialogue and personal narratives

np_max-act · gemini-2.0-flash

This neuron doesn’t activate for any text—it appears to be completely inactive (a “dead” neuron).

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

�

-0.07

(cursor

-0.07

.release

-0.07

(',')[

-0.06

LEGRO

-0.06

 family

-0.06

นอ

-0.06

 روی

-0.06

 campaigned

-0.06

(style

-0.06

POSITIVE LOGITS

SETTINGS

0.07

ста

0.07

_singular

0.07

opo

0.06

indh

0.06

uno

0.06

ап

0.06

icio

0.06

 lymph

0.06

보

0.06

Activations Density 0.074%

Dialogue and personal narratives

This neuron doesn’t activate for any text—it appears to be completely inactive (a “dead” neuron).

No Comments

No Known Activations