INDEX

Explanations

credit

np_max-act · gemini-2.0-flash

The neuron activates on occurrences of the word “credit,” especially when discussing credit scores or credit‐related topics.

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

mí

-0.07

农

-0.07

 Stark

-0.07

MK

-0.07

ウォ

-0.07

 interventions

-0.07

 Merr

-0.06

าระ

-0.06

 yandan

-0.06

SMA

-0.06

POSITIVE LOGITS

 credit

0.07

.clients

0.07

vin

0.06

uels

0.06

 discredit

0.06

 напрям

0.06

ickets

0.06

 matcher

0.06

 discounts

0.06

تون

0.06

Activations Density 0.004%

credit

The neuron activates on occurrences of the word “credit,” especially when discussing credit scores or credit‐related topics.

No Comments

No Known Activations