INDEX

Explanations

Physics/Spectroscopy

np_max-act · gemini-2.0-flash

This neuron activates on technical terms related to spectroscopic measurements and electronic structure in scientific texts.

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

Radi

-0.08

.pose

-0.07

permissions

-0.06

座

-0.06

SK

-0.06

_DGRAM

-0.06

SAN

-0.06

Pt

-0.06

ColumnType

-0.06

owo

-0.06

POSITIVE LOGITS

 разработ

0.07

-message

0.06

-ie

0.06

 Nokia

0.06

 solder

0.06

.MIN

0.06

assemble

0.06

 assure

0.06

WARD

0.06

<!--<

0.06

Activations Density 0.004%

Physics/Spectroscopy

This neuron activates on technical terms related to spectroscopic measurements and electronic structure in scientific texts.

No Comments

No Known Activations

Physics/Spectroscopy

This neuron activates on technical terms related to spectroscopic measurements and electronic structure in scientific texts.

No Comments

No Known Activations