INDEX

Explanations

">"

np_max-act · gemini-2.0-flash

The neuron fires on HTML documentation navigation link labels (e.g. sidebar/top-nav menu items like “Overview,” “Package,” “Class,” “Skip navigation links,” etc.).

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

-0.06

riors

-0.06

-wage

-0.06

'im

-0.06

 sın

-0.06

 Glide

-0.06

 Garr

-0.06

_DOWN

-0.06

Day

-0.06

_duration

-0.06

POSITIVE LOGITS

.InteropServices

0.07

collect

0.07

Behaviour

0.07

.Abstractions

0.06

_ALLOC

0.06

删除

0.06

さ

0.06

 الحل

0.06

lac

0.06

-establish

0.06

Activations Density 0.010%

">"

The neuron fires on HTML documentation navigation link labels (e.g. sidebar/top-nav menu items like “Overview,” “Package,” “Class,” “Skip navigation links,” etc.).

No Comments

No Known Activations