INDEX

Explanations

Citations and references

np_max-act · gemini-2.0-flash

The neuron selectively activates on numerical tokens (e.g. citation years, reference numbers, or floating‐point values) in the text.

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

 THREAD

-0.07

 professional

-0.07

헤

-0.06

ลล

-0.06

 decimals

-0.06

Imp

-0.06

TIME

-0.06

Top

-0.06

ITH

-0.06

ram

-0.06

POSITIVE LOGITS

*k

0.07

/tinyos

0.07

.config

0.06

 Falcon

0.06

 içeri

0.06

 hoops

0.06

 sonunda

0.06

/"↵

0.06

_EVAL

0.06

 поэтому

0.06

Activations Density 0.014%

Citations and references

The neuron selectively activates on numerical tokens (e.g. citation years, reference numbers, or floating‐point values) in the text.

No Comments

No Known Activations