INDEX

Explanations

ees

np_max-act · gemini-2.0-flash

The neuron flags mentions of training program components and participants—especially terms like “training,” “program,” “pre‐doctoral,” “post‐doctoral,” and related trainee references.

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

ока

-0.06

gent

-0.06

istring

-0.06

 estrogen

-0.06

MatrixMode

-0.06

eria

-0.06

авлива

-0.06

ICA

-0.06

非

-0.05

Ố

-0.05

POSITIVE LOGITS

楽し

0.07

ชร

0.07

.ToUpper

0.06

 اداره

0.06

tainment

0.06

 бет

0.06

 Loose

0.06

七

0.06

召

0.06

']->

0.06

Activations Density 0.017%

ees

The neuron flags mentions of training program components and participants—especially terms like “training,” “program,” “pre‐doctoral,” “post‐doctoral,” and related trainee references.

No Comments

No Known Activations