INDEX

Explanations

Cancer research

np_max-act · gemini-2.0-flash

This neuron is highly activated by mentions of specific cell line identifiers (e.g., HCT116, U87, SW620, MDA-MB-231) and their associated alphanumeric codes.

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

 parity

-0.07

 truth

-0.07

га

-0.07

 creds

-0.06

 vết

-0.06

 antes

-0.06

-best

-0.06

 Sanctuary

-0.06

.trace

-0.06

-energy

-0.06

POSITIVE LOGITS

virt

0.07

озя

0.07

공부

0.07

Oops

0.06

 صلى

0.06

ث

0.06

 tham

0.06

 pData

0.06

 상담

0.06

Activations Density 0.019%

Cancer research

This neuron is highly activated by mentions of specific cell line identifiers (e.g., HCT116, U87, SW620, MDA-MB-231) and their associated alphanumeric codes.

No Comments

No Known Activations