INDEX

Explanations

The article "A"

np_max-act · gemini-2.0-flash

The neuron fires on backslash characters (i.e. the “\” path‐separator tokens in file/path strings).

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

 sketches

-0.07

Feel

-0.06

 Werner

-0.06

 coordination

-0.06

 pasta

-0.06

amine

-0.06

ense

-0.06

 orange

-0.06

 propulsion

-0.06

 Workers

-0.06

POSITIVE LOGITS

=forms

0.07

 handleMessage

0.06

xed

0.06

eted

0.06

Feat

0.06

_GENERIC

0.06

pkt

0.06

ाँ

0.06

xae

0.06

_credit

0.06

Activations Density 0.007%

The article "A"

The neuron fires on backslash characters (i.e. the “\” path‐separator tokens in file/path strings).

No Comments

No Known Activations