INDEX

Explanations

symbols

np_max-act · gemini-2.0-flash

This neuron detects conversation boundary or control tokens (e.g. the <|eot_id|> end-of-text markers).

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

ffmpeg

-0.08

 Messenger

-0.07

 کننده

-0.07

 خارجی

-0.06

_topology

-0.06

 fflush

-0.06

 Pediatric

-0.06

なら

-0.06

atoms

-0.06

Collider

-0.06

POSITIVE LOGITS

ुर

0.07

ACA

0.06

 Cait

0.06

 fixed

0.06

์↵

0.06

 setState

0.06

=DB

0.06

пра

0.06

 важ

0.06

 January

0.06

Activations Density 0.124%

symbols

This neuron detects conversation boundary or control tokens (e.g. the <|eot_id|> end-of-text markers).

No Comments

No Known Activations