INDEX

Explanations

code

np_max-act · gemini-2.0-flash

This neuron activates on programming-language code snippets (e.g. tokens like “function,” “var,” “Dim,” braces, code syntax).

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

奇

-0.06

두

-0.06

�

-0.06

�

-0.06

 passport

-0.06

_TH

-0.06

 checkboxes

-0.06

ecs

-0.06

ujete

-0.06

 Fuck

-0.06

POSITIVE LOGITS

Ext

0.07

.mapping

0.07

PRI

0.06

,…

0.06

_date

0.06

 {↵↵↵↵

0.06

urrection

0.06

	query

0.06

[[

0.06

Activations Density 0.075%

code

This neuron activates on programming-language code snippets (e.g. tokens like “function,” “var,” “Dim,” braces, code syntax).

No Comments

No Known Activations