INDEX

Explanations

LICENSE

np_max-act · gemini-2.0-flash

This neuron fires on references to the “LICENSE” file in source‐code headers.

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

 cumshot

-0.07

isbn

-0.07

куль

-0.06

ิโน

-0.06

đa

-0.06

Tools

-0.06

 đẳng

-0.06

情

-0.06

 filtering

-0.06

tik

-0.06

POSITIVE LOGITS

_esc

0.06

IDDLE

0.06

"↵↵↵

0.06

_extension

0.06

())))↵

0.06

BagConstraints

0.06

 نی

0.06

################

0.06

—is

0.06

Activations Density 0.002%

LICENSE

This neuron fires on references to the “LICENSE” file in source‐code headers.

No Comments

No Known Activations