INDEX

Explanations

ol

np_max-act · gemini-2.0-flash

This neuron detects mentions of “monolayer” (i.e., self-assembled or Langmuir–Blodgett molecular monolayer) contexts.

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

 Destination

-0.07

azing

-0.06

яз

-0.06

.activity

-0.06

né

-0.06

******
↵

-0.06

 attain

-0.06

 Sega

-0.06

=explode

-0.06

POSITIVE LOGITS

賞

0.07

okit

0.07

_disp

0.06

 automated

0.06

 elapsedTime

0.06

Primitive

0.06

 тяж

0.06

"#{

0.06

|=↵

0.06

/gui

0.06

Activations Density 0.002%

ol

This neuron detects mentions of “monolayer” (i.e., self-assembled or Langmuir–Blodgett molecular monolayer) contexts.

No Comments

No Known Activations