INDEX

Explanations

AAAAAAAA

np_max-act · gemini-2.0-flash

This neuron primarily responds to individual non-ASCII or accented characters (unusual Unicode symbols) in the input.

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

퓨

-0.07

 перес

-0.06

debit

-0.06

THREAD

-0.06

otyp

-0.06

κου

-0.06

.getStatusCode

-0.06

andelier

-0.06

ेड

-0.06

ged

-0.06

POSITIVE LOGITS

 лекар

0.07

leftrightarrow

0.07

 disclosures

0.06

()

0.06

 skills

0.06

 simply

0.06

规模

0.06

*\

0.06

()}

0.06

 inevitable

0.06

Activations Density 0.007%

AAAAAAAA

This neuron primarily responds to individual non-ASCII or accented characters (unusual Unicode symbols) in the input.

No Comments

No Known Activations