INDEX

Explanations

in

np_max-act · gemini-2.0-flash

This neuron detects descriptions of experimental manipulations—especially stereotaxic or microinjection procedures into specific brain regions.

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

itlement

-0.07

portfolio

-0.06

業

-0.06

(index

-0.06

Non

-0.06

(DB

-0.06

 contractual

-0.06

 револю

-0.06

 oral

-0.06

Pg

-0.06

POSITIVE LOGITS

 parties

0.06

ılmaktadır

0.06

_features

0.06

救

0.06

_clear

0.06

.");

0.06

BODY

0.06

 قص

0.06

_feat

0.06

'][]

0.06

Activations Density 0.012%

in

This neuron detects descriptions of experimental manipulations—especially stereotaxic or microinjection procedures into specific brain regions.

No Comments

No Known Activations