INDEX

Explanations

cere

np_max-act · gemini-2.0-flash

references to neurochemical and metabolic changes associated with brain functions and conditions.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

The neuron selectively activates on occurrences of “cere” as the prefix of brain‐related anatomical terms (e.g. cerebral, cerebellum, cerebrospinal).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.nb

-0.07

LX

-0.07

-ons

-0.07

 imkân

-0.07

 López

-0.07

JSX

-0.07

switch

-0.07

 strikeouts

-0.07

プ

-0.07

onz

-0.07

POSITIVE LOGITS

 cere

0.10

 cereal

0.10

ere

0.09

 cram

0.07

ρε

0.07

\E

0.07

 gente

0.07

 Cure

0.07

 Cree

0.07

 Τε

0.07

Activations Density 0.004%

cere

references to neurochemical and metabolic changes associated with brain functions and conditions.

The neuron selectively activates on occurrences of “cere” as the prefix of brain‐related anatomical terms (e.g. cerebral, cerebellum, cerebrospinal).

No Comments

No Known Activations