INDEX

Explanations

prepositions

np_max-act · gemini-2.0-flash

This neuron selectively activates on technical or scientific text that includes numeric, quantitative, or highly specific measurements (dates, figures, concentrations, or other precise data) within formal descriptions.

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

ิลล

-0.07

peated

-0.06

随

-0.06

vě

-0.06

änn

-0.06

CSV

-0.06

ργ

-0.06

Std

-0.06

}&

-0.06

POSITIVE LOGITS

ENTRY

0.07

#----------------------------------------------------------------------------

0.07

Stage

0.06

vur

0.06

τηση

0.06

_CODES

0.06

 [↵↵

0.06

webs

0.06

Modificar

0.06

Snackbar

0.06

Activations Density 0.574%

prepositions

This neuron selectively activates on technical or scientific text that includes numeric, quantitative, or highly specific measurements (dates, figures, concentrations, or other precise data) within formal descriptions.

No Comments

No Known Activations

prepositions

This neuron selectively activates on technical or scientific text that includes numeric, quantitative, or highly specific measurements (dates, figures, concentrations, or other precise data) within formal descriptions.

No Comments

No Known Activations