INDEX

Explanations

Code snippets

np_max-act · gemini-2.0-flash

The neuron detects tokens that are parts of hexadecimal identifiers (e.g. GUID or SHA strings).

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

 pretended

-0.06

Anderson

-0.06

“You

-0.06

 Titans

-0.06

 goalie

-0.06

	list

-0.06

.download

-0.06

registers

-0.06

_BINDING

-0.06

QUE

-0.06

POSITIVE LOGITS

 pocházet

0.07

 cohesion

0.07

lz

0.06

das

0.06

 شروع

0.06

.Basic

0.06

mobx

0.06

.assertIs

0.06

orean

0.06

 beim

0.06

Activations Density 0.016%

Code snippets

The neuron detects tokens that are parts of hexadecimal identifiers (e.g. GUID or SHA strings).

No Comments

No Known Activations