INDEX

Explanations

9

np_max-act · gemini-2.0-flash

This neuron specifically detects fragments of UTF-8 hex escape sequences (e.g. “xe2”, “x80”, “x9c”) that encode punctuation characters.

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

 Marseille

-0.06

Ａ

-0.06

#----------------------------------------------------------------

-0.06

]:
↵

-0.06

Matchers

-0.06

ンプ

-0.06

mathrm

-0.06

(*(

-0.06

Containers

-0.06

 пох

-0.06

POSITIVE LOGITS

_Close

0.08

wi

0.07

ey

0.07

بس

0.06

米

0.06

 skewed

0.06

ratings

0.06

dah

0.06

essay

0.06

friend

0.06

Activations Density 0.004%

9

This neuron specifically detects fragments of UTF-8 hex escape sequences (e.g. “xe2”, “x80”, “x9c”) that encode punctuation characters.

No Comments

No Known Activations

9

This neuron specifically detects fragments of UTF-8 hex escape sequences (e.g. “xe2”, “x80”, “x9c”) that encode punctuation characters.

No Comments

No Known Activations