INDEX

Explanations

al

np_max-act · gemini-2.0-flash

The neuron fires on occurrences of the word “conformal” (i.e. its subword tokens con–form–al).

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

 flavored

-0.07

eparator

-0.07

Enumer

-0.07

یزی

-0.06

edException

-0.06

has

-0.06

 helping

-0.06

라이

-0.06

лися

-0.06

readcr

-0.06

POSITIVE LOGITS

CIM

0.07

mA

0.07

Ví

0.07

ヽ

0.06

 persuasive

0.06

 Costs

0.06

	unset

0.06

 Προ

0.06

 securely

0.06

Base

0.06

Activations Density 0.001%

al

The neuron fires on occurrences of the word “conformal” (i.e. its subword tokens con–form–al).

No Comments

No Known Activations