INDEX

Explanations

instructions

np_max-act · gemini-2.0-flash

This neuron detects sentence‐initial disclaimer or elaboration phrases (e.g. “It’s important to note…”).

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

Tab

-0.07

pid

-0.06

Pictures

-0.06

tk

-0.06

 vás

-0.06

 tapes

-0.06

ву

-0.06

_handler

-0.06

 curry

-0.06

 Horde

-0.06

POSITIVE LOGITS

EE

0.07

egal

0.07

라마

0.06

免费

0.06

地區

0.06

 FLAC

0.06

~↵

0.06

errupt

0.06

 *);↵

0.06

.ACCESS

0.06

Activations Density 0.049%

instructions

This neuron detects sentence‐initial disclaimer or elaboration phrases (e.g. “It’s important to note…”).

No Comments

No Known Activations