INDEX

Explanations

Product descriptions or ads

np_max-act · gemini-2.0-flash

phrases related to craft and DIY projects.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

The neuron activates on words naming or describing product design elements—e.g. “pattern,” “ideas,” “design,” “designs,” “cute,” “whimsical,” 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

osals

-0.07

 tail

-0.07

ΟΚ

-0.06

 clue

-0.06

eno

-0.06

 concerts

-0.06

uen

-0.06

_times

-0.06

Guest

-0.06

periments

-0.06

POSITIVE LOGITS

entanyl

0.07

UGH

0.06

 görev

0.06

_simple

0.06

μπο

0.06

*/↵↵↵

0.06

 Во

0.06

�

0.06

＿＿

0.06

 unleashed

0.06

Activations Density 0.069%

Product descriptions or ads

phrases related to craft and DIY projects.

The neuron activates on words naming or describing product design elements—e.g. “pattern,” “ideas,” “design,” “designs,” “cute,” “whimsical,” etc.

No Comments

No Known Activations