INDEX

Explanations

anatomy

np_max-act · gemini-2.0-flash

The neuron strongly activates on anatomical descriptions and studies—especially words denoting anatomy, anatomical landmarks or variations.

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

address

-0.07

.adapter

-0.07

ond

-0.06

_than

-0.06

CACHE

-0.06

ाण

-0.06

refs

-0.06

�

-0.06

-submit

-0.06

vt

-0.06

POSITIVE LOGITS

 Ihrer

0.07

NM

0.07

 双线

0.06

][(

0.06

 Brill

0.06

PageRoute

0.06

_pll

0.06

CFR

0.06

_ELEM

0.06

現

0.06

Activations Density 0.023%

anatomy

The neuron strongly activates on anatomical descriptions and studies—especially words denoting anatomy, anatomical landmarks or variations.

No Comments

No Known Activations