INDEX

Explanations

same

np_max-act · gemini-2.0-flash

This neuron fires on occurrences of the phrase “the same way” (and similar wording) indicating identical presentation.

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

 round

-0.06

線

-0.06

 towards

-0.06

 Strange

-0.06

elial

-0.06

ToDelete

-0.05

 crowded

-0.05

KD

-0.05

_ud

-0.05

 Örneğin

-0.05

POSITIVE LOGITS

”)

0.07

_icons

0.07

");

0.07

 AppBar

0.07

.removeListener

0.06

 kommt

0.06

 изменения

0.06

roke

0.06

ภ

0.06

zzarella

0.06

Activations Density 0.001%

same

This neuron fires on occurrences of the phrase “the same way” (and similar wording) indicating identical presentation.

No Comments

No Known Activations

same

This neuron fires on occurrences of the phrase “the same way” (and similar wording) indicating identical presentation.

No Comments

No Known Activations