INDEX

Explanations

back

np_max-act · gemini-2.0-flash

The neuron fires on wording that indicates reverting or restoring a prior transformation—especially phrases like “back,” “convert … back,” or “build … back.”

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

�

-0.06

Bh

-0.06

iro

-0.06

 Fletcher

-0.06

 Wonderland

-0.06

-wow

-0.06

 Trap

-0.06

 ALOG

-0.06

 Bombay

-0.06

POSITIVE LOGITS

 grateful

0.07

摘

0.06

 contro

0.06

(constants

0.06

regor

0.06

уляр

0.06

 вже

0.06

-reviewed

0.06

 karena

0.06

_UNICODE

0.06

Activations Density 0.032%

back

The neuron fires on wording that indicates reverting or restoring a prior transformation—especially phrases like “back,” “convert … back,” or “build … back.”

No Comments

No Known Activations