INDEX

Explanations

code

np_max-act · gemini-2.0-flash

This neuron fires on Swift optional‐binding “guard let” patterns.

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

ariance

-0.08

inden

-0.07

 Pose

-0.07

 Finch

-0.06

:UITableView

-0.06

uncate

-0.06

 Nights

-0.06

itives

-0.06

 pronunciation

-0.06

 Hermione

-0.06

POSITIVE LOGITS

(...

0.07

頁

0.06

.gb

0.06

Akt

0.06

__(*

0.06

)arg

0.06

�

0.06

 Gluten

0.06

]*(

0.06

ngx

0.06

Activations Density 0.109%

code

This neuron fires on Swift optional‐binding “guard let” patterns.

No Comments

No Known Activations