INDEX

Explanations

HTML or web development

np_max-act · gemini-2.0-flash

The neuron selectively activates on the model’s internal control tokens and metadata markers (e.g. “<|start_header_id|>”, “<|begin_of_text|>”, etc.).

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

्थन

-0.07

.sys

-0.06

.bank

-0.06

粗

-0.06

gap

-0.06

textContent

-0.06

 Jump

-0.06

 हव

-0.06

.Owner

-0.06

 Manip

-0.06

POSITIVE LOGITS

(@"%@",

0.07

 naken

0.07

dirname

0.07

 янва

0.07

,’’

0.07

 controversial

0.07

forman

0.06

"He

0.06

ven

0.06

abi

0.06

Activations Density 0.021%

HTML or web development

The neuron selectively activates on the model’s internal control tokens and metadata markers (e.g. “<|start_header_id|>”, “<|begin_of_text|>”, etc.).

No Comments

No Known Activations