INDEX

Explanations

relay

np_max-act · gemini-2.0-flash

The neuron consistently activates on occurrences of the word “relay” (in any casing or morphological form).

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

 province

-0.07

.Open

-0.07

ombok

-0.07

푸

-0.07

 tumor

-0.06

ITTLE

-0.06

OOD

-0.06

PRE

-0.06

 Find

-0.06

 ков

-0.06

POSITIVE LOGITS

 relay

0.15

 Relay

0.10

 recycling

0.08

 telemetry

0.08

 поє

0.08

 paralle

0.08

elan

0.07

lej

0.07

 Telegraph

0.07

 relational

0.07

Activations Density 0.003%

relay

The neuron consistently activates on occurrences of the word “relay” (in any casing or morphological form).

No Comments

No Known Activations