INDEX

Explanations

Quotation marks

np_max-act · gemini-2.0-flash

This neuron never activates on any input—it appears to be completely inactive.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 soit

-0.06

仕

-0.06

 เป

-0.06

 reorder

-0.06

 đơn

-0.06

Normalization

-0.06

 sponge

-0.06

Wah

-0.05

ocused

-0.05

_buy

-0.05

POSITIVE LOGITS

扫

0.07

 Antony

0.07

(cursor

0.07

 rugged

0.07

imensional

0.06

↵

0.06

Utt

0.06

utan

0.06

Activations Density 0.030%

Quotation marks

This neuron never activates on any input—it appears to be completely inactive.

No Comments

No Known Activations

Quotation marks

This neuron never activates on any input—it appears to be completely inactive.

No Comments

No Known Activations