INDEX

Explanations

:

np_max-act · gemini-2.0-flash

The neuron is highly sensitive to the colon separators used in XML namespace declarations (i.e. the “:” tokens in xmlns attributes).

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

con

-0.08

'].$

-0.08

 stray

-0.07

edii

-0.07

)}}

-0.07

�

-0.07

ВС

-0.06

 getText

-0.06

);↵↵↵↵↵

-0.06

 originated

-0.06

POSITIVE LOGITS

 Frem

0.06

 elevation

0.06

터

0.06

命周期

0.06

antages

0.06

_index

0.06

kop

0.06

战

0.06

异常

0.06

(stop

0.06

Activations Density 0.001%

:

The neuron is highly sensitive to the colon separators used in XML namespace declarations (i.e. the “:” tokens in xmlns attributes).

No Comments

No Known Activations