INDEX

Explanations

loops and cycles

np_max-act · gemini-2.0-flash

This neuron fires on words describing a round-robin (cyclic) selection process—e.g. “round-robin,” “bin,” “selects,” “colors.”

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

.time

-0.07

EST

-0.07

.Double

-0.07

_resize

-0.07

 Bayesian

-0.06

 seamless

-0.06

 Wins

-0.06

	renderer

-0.06

escription

-0.06

 Playback

-0.06

POSITIVE LOGITS

 permutations

0.06

 pushViewController

0.06

 Sınıf

0.06

[C

0.06

は

0.06

문

0.06

�체

0.06

 behaves

0.06

押

0.06

━�

0.06

Activations Density 0.028%

loops and cycles

This neuron fires on words describing a round-robin (cyclic) selection process—e.g. “round-robin,” “bin,” “selects,” “colors.”

No Comments

No Known Activations