INDEX

Explanations

The

np_max-act · gemini-2.0-flash

This neuron detects section or subsection headings and title elements (e.g. roman numerals, “Part,” “Chapter,” and heading words like “Effect,” “Comparison,” “Clinical,” etc.) in a document.

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

 نام

-0.06

 which

-0.06

ax

-0.06

(...

-0.06

/ms

-0.06

 surplus

-0.06

费

-0.06

 disciplined

-0.06

 utmost

-0.06

 spokeswoman

-0.06

POSITIVE LOGITS

_fb

0.07

 DefaultValue

0.07

[Boolean

0.07

 bụi

0.07

_gc

0.07

 acompanh

0.06

.GetLength

0.06

skin

0.06

 dejtings

0.06

.setChecked

0.06

Activations Density 0.027%

The

This neuron detects section or subsection headings and title elements (e.g. roman numerals, “Part,” “Chapter,” and heading words like “Effect,” “Comparison,” “Clinical,” etc.) in a document.

No Comments

No Known Activations