INDEX

Explanations

opher

np_max-act · gemini-2.0-flash

The neuron detects occurrences of tocopherol-related terms (e.g., “toc,” “tocopherol,” “α-tocopherol,” 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

JWT

-0.07

-my

-0.07

 Padres

-0.07

 thơm

-0.06

 Arbor

-0.06

↔

-0.06

를

-0.06

 Bust

-0.06

PopupMenu

-0.06

 MEDIATEK

-0.06

POSITIVE LOGITS

0.06

_PH

0.06

É

0.06

 Nicholas

0.06

_MOUNT

0.06

üh

0.06

querque

0.06

 χρησιμοποι

0.06

owment

0.06

Activations Density 0.001%

opher

The neuron detects occurrences of tocopherol-related terms (e.g., “toc,” “tocopherol,” “α-tocopherol,” etc.).

No Comments

No Known Activations

opher

The neuron detects occurrences of tocopherol-related terms (e.g., “toc,” “tocopherol,” “α-tocopherol,” etc.).

No Comments

No Known Activations