INDEX

Explanations

Positive sentiment

np_max-act · gemini-2.0-flash

The neuron never activates—it does not respond to any tokens or patterns in the text.

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

ける

-0.07

stitial

-0.06

文字

-0.06

 Aviation

-0.06

 oath

-0.06

 demonic

-0.06

 धर

-0.06

увався

-0.06

opic

-0.06

柴

-0.06

POSITIVE LOGITS

 sscanf

0.07

pear

0.07

 —↵

0.07

EHICLE

0.06

 poke

0.06

.loggedIn

0.06

 Defines

0.06

 recep

0.06

(Main

0.06

Activations Density 0.054%

Positive sentiment

The neuron never activates—it does not respond to any tokens or patterns in the text.

No Comments

No Known Activations