INDEX

Explanations

req

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of the single-letter identifier “r” (commonly used as the Request parameter name) in Go code.

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

ока

-0.07

 grpc

-0.07

üle

-0.07

,arg

-0.06

 occupation

-0.06

Errors

-0.06

#a

-0.06

 guiding

-0.06

vog

-0.06

 Crist

-0.06

POSITIVE LOGITS

 addCriterion

0.07

 más

0.06

.localtime

0.06

nak

0.06

 phim

0.06

 зам

0.06

 Seks

0.06

の子

0.06

모

0.06

('+

0.06

Activations Density 0.001%

req

This neuron activates on occurrences of the single-letter identifier “r” (commonly used as the Request parameter name) in Go code.

No Comments

No Known Activations