INDEX

Explanations

Research studies

np_max-act · gemini-2.0-flash

The main thing this neuron detects is terminology about dynamic or time‐varying representations—words and phrases that describe change or dynamics (e.g. “dynamic,” “changes,” “changing,” “representation,” etc.) in technical contexts.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

وير

-0.06

.Person

-0.06

 maintenance

-0.06

Loaded

-0.06

Autoresizing

-0.06

 playoffs

-0.06

 Yours

-0.06

 freezes

-0.06

 Melee

-0.06

cccc

-0.06

POSITIVE LOGITS

_theta

0.07

.ins

0.06

方法

0.06

воз

0.06

<(),

0.06

:/:

0.06

 актив

0.06

_TRIANGLES

0.06

чай

0.06

Activations Density 0.099%

Research studies

The main thing this neuron detects is terminology about dynamic or time‐varying representations—words and phrases that describe change or dynamics (e.g. “dynamic,” “changes,” “changing,” “representation,” etc.) in technical contexts.

No Comments

No Known Activations