INDEX

Explanations

packaging

np_max-act · gemini-2.0-flash

The neuron is effectively inactive and does not respond to any tokens.

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

iance

-0.07

 python

-0.07

-group

-0.06

aec

-0.06

 Positive

-0.06

Thu

-0.06

 PRIMARY

-0.06

 coronary

-0.06

("").

-0.06

 ruby

-0.06

POSITIVE LOGITS

梯

0.07

TexParameter

0.07

�

0.07

nage

0.06

 unfairly

0.06

 Seiten

0.06

蜘蛛词

0.06

 defaultManager

0.06

爱

0.06

Activations Density 0.006%

packaging

The neuron is effectively inactive and does not respond to any tokens.

No Comments

No Known Activations