INDEX

Explanations

ocular

np_max-act · gemini-2.0-flash

The neuron selectively activates on occurrences of the word “ocular” (especially in “intraocular”), flagging mentions of intraocular measurements.

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

 chan

-0.07

latent

-0.07

KT

-0.07

Adjacent

-0.07

enate

-0.06

 Brigade

-0.06

arge

-0.06

 سید

-0.06

报道

-0.06

(MediaType

-0.06

POSITIVE LOGITS

_mini

0.06

 lookahead

0.06

 alkal

0.06

TouchEvent

0.06

!";
↵

0.06

OnClick

0.06

↵

0.06

 tutar

0.06

authentication

0.06

!";↵

0.06

Activations Density 0.001%

ocular

The neuron selectively activates on occurrences of the word “ocular” (especially in “intraocular”), flagging mentions of intraocular measurements.

No Comments

No Known Activations

ocular

The neuron selectively activates on occurrences of the word “ocular” (especially in “intraocular”), flagging mentions of intraocular measurements.

No Comments

No Known Activations