INDEX

Explanations

DV

np_max-act · gemini-2.0-flash

The neuron detects chunks of Base64‐encoded data inside PEM blocks (the long uppercase/alphanumeric lines in certificate or key delimiters).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

opc

-0.06

.portal

-0.06

ectors

-0.06

logan

-0.06

lm

-0.06

ิทยาล

-0.06

亡

-0.06

-*

-0.06

Pit

-0.06

 mortality

-0.06

POSITIVE LOGITS

Lane

0.07

illions

0.07

 minh

0.06

 calories

0.06

 Computational

0.06

 Plain

0.06

	channel

0.06

Rep

0.06

(fname

0.06

(Syntax

0.06

Activations Density 0.002%

DV

The neuron detects chunks of Base64‐encoded data inside PEM blocks (the long uppercase/alphanumeric lines in certificate or key delimiters).

No Comments

No Known Activations