INDEX

Explanations

possessive pronouns

np_max-act · gemini-2.0-flash

The neuron is triggered almost exclusively by numeric tokens in decimal form (floating‐point numbers).

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

 Counts

-0.07

 спе

-0.07

 meiden

-0.07

(simp

-0.07

.Db

-0.07

/help

-0.07

style

-0.07

 hookers

-0.07

じゃない

-0.07

급

-0.06

POSITIVE LOGITS

ческой

0.07

Σ

0.06

�

0.06

UB

0.06

cmb

0.06

 фар

0.06

ателя

0.06

 culinary

0.06

displayText

0.06

Outlined

0.06

Activations Density 0.009%

possessive pronouns

The neuron is triggered almost exclusively by numeric tokens in decimal form (floating‐point numbers).

No Comments

No Known Activations

possessive pronouns

The neuron is triggered almost exclusively by numeric tokens in decimal form (floating‐point numbers).

No Comments

No Known Activations