INDEX

Explanations

interpretation

np_max-act · gemini-2.0-flash

This neuron activates on language about interpreting or making sense of test/study results.

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

 REQUEST

-0.07

물

-0.07

 potrav

-0.06

浦

-0.06

 hoàn

-0.06

 можливість

-0.06

 pudd

-0.06

@store

-0.06

γον

-0.06

POSITIVE LOGITS

 Interpret

0.08

 GENERAL

0.07

PAS

0.07

Advertisements

0.07

 blob

0.06

acom

0.06

 COMM

0.06

 somewhere

0.06

τής

0.06

 Cooper

0.06

Activations Density 0.021%

interpretation

This neuron activates on language about interpreting or making sense of test/study results.

No Comments

No Known Activations