INDEX

Explanations

output

np_max-act · gemini-2.0-flash

This neuron fires on mentions of command-line utility names (often in backticks) used for system diagnostics, e.g. journalctl, lspci, lsblk, 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

Decoration

-0.07

ained

-0.07

 влаж

-0.07

 seam

-0.07

кових

-0.06

초

-0.06

说的

-0.06

_codes

-0.06

 visions

-0.06

 ід

-0.06

POSITIVE LOGITS

squ

0.06

\"

0.06

 organiz

0.06

Xã

0.06

 Consumer

0.06

AAC

0.06

ividual

0.06

empre

0.06

 outbound

0.06

 характ

0.06

Activations Density 0.033%

output

This neuron fires on mentions of command-line utility names (often in backticks) used for system diagnostics, e.g. journalctl, lspci, lsblk, etc.

No Comments

No Known Activations