INDEX

Explanations

apt

np_max-act · gemini-2.0-flash

The neuron activates on occurrences of the “apt” package‐manager commands (e.g. “sudo apt update/install”) in Ubuntu setup instructions.

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

Photon

-0.08

.middle

-0.07

 Gover

-0.07

 redistribution

-0.07

ского

-0.07

Router

-0.07

 threshold

-0.07

 relativ

-0.07

-lines

-0.07

buffer

-0.07

POSITIVE LOGITS

($.

0.06

_\

0.06

 Tear

0.06

int

0.06

(va

0.06

 komm

0.06

(dd

0.06

noinspection

0.06

âm

0.06

.Vertex

0.05

Activations Density 0.002%

apt

The neuron activates on occurrences of the “apt” package‐manager commands (e.g. “sudo apt update/install”) in Ubuntu setup instructions.

No Comments

No Known Activations