INDEX

Explanations

Explicit/offensive content

np_max-act · gemini-2.0-flash

The neuron specializes in detecting special metadata markers that denote header boundaries (e.g. the `<|start_header_id|>` and `<|end_header_id|>` tokens).

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

您的

-0.07

ungkin

-0.06

)

↵

-0.06

ával

-0.06

 selects

-0.06

 vyšší

-0.06

 дел

-0.06

мерикан

-0.06

 Magnetic

-0.06

POSITIVE LOGITS

-times

0.07

AW

0.06

_teacher

0.06

optimize

0.06

 torrent

0.06

 spontaneously

0.06

_HOOK

0.06

toJson

0.06

 madrid

0.06

FTER

0.06

Activations Density 0.080%

Explicit/offensive content

The neuron specializes in detecting special metadata markers that denote header boundaries (e.g. the `<|start_header_id|>` and `<|end_header_id|>` tokens).

No Comments

No Known Activations