INDEX

Explanations

Field

np_max-act · gemini-2.0-flash

The neuron activates on the document’s section header “Technical Field,” i.e. it detects the start of the technical field section.

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

ophys

-0.07

SUMER

-0.07

ала

-0.07

Tr

-0.06

Sit

-0.06

ipients

-0.06

unate

-0.06

oner

-0.06

peare

-0.06

 topped

-0.06

POSITIVE LOGITS

Bav

0.06

βα

0.06

 experienced

0.06

贝

0.06

 prolong

0.06

(props

0.06

;",↵

0.06

 textures

0.06

↵

0.06

 }}"></

0.06

Activations Density 0.001%

Field

The neuron activates on the document’s section header “Technical Field,” i.e. it detects the start of the technical field section.

No Comments

No Known Activations