INDEX

Explanations

medical/scientific contexts

np_max-act · gemini-2.0-flash

The neuron activates whenever it encounters the letter sequence “imp” (as part of words like “impotence,” “impairs,” etc.).

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

roma

-0.08

erea

-0.08

瑟

-0.08

ара

-0.08

 Xavier

-0.08

 Sever

-0.08

Sea

-0.08

yla

-0.08

POSITIVE LOGITS

ind

0.08

0.07

Ind

0.07

.Ass

0.07

ob

0.07

.All

0.07

ASS

0.07

und

0.07

.OrdinalIgnoreCase

0.07

ell

0.07

Activations Density 0.174%

medical/scientific contexts

The neuron activates whenever it encounters the letter sequence “imp” (as part of words like “impotence,” “impairs,” etc.).

No Comments

No Known Activations