INDEX

Explanations

-C

np_max-act · gemini-2.0-flash

The neuron activates when spotting mentions of the programming language Objective-C (i.e. the “Objective” + “C” tokens in that context).

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

ASTER

-0.07

puter

-0.06

Wilson

-0.06

假

-0.06

또

-0.06

.btnAdd

-0.06

 Week

-0.06

्पर

-0.06

返

-0.06

getClient

-0.06

POSITIVE LOGITS

ould

0.07

 objc

0.07

 chín

0.07

(sym

0.07

qm

0.07

 contrary

0.06

 Exercises

0.06

aviors

0.06

 complying

0.06

quoise

0.06

Activations Density 0.002%

-C

The neuron activates when spotting mentions of the programming language Objective-C (i.e. the “Objective” + “C” tokens in that context).

No Comments

No Known Activations