INDEX

Explanations

notion

np_max-act · gemini-2.0-flash

The neuron flags domain‐specific technical jargon and formal section‐heading words common in academic or scientific writing.

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

ienda

-0.07

reh

-0.06

eğ

-0.06

 boto

-0.06

ิง

-0.06

 obtaining

-0.06

 tento

-0.06

वत

-0.06

asal

-0.06

 vals

-0.06

POSITIVE LOGITS

タン

0.06

UPC

0.06

 hefty

0.06

 नए

0.06

BJP

0.06

-tags

0.06

 itemBuilder

0.06

_BINARY

0.06

 outskirts

0.06

-purple

0.06

Activations Density 0.098%

notion

The neuron flags domain‐specific technical jargon and formal section‐heading words common in academic or scientific writing.

No Comments

No Known Activations