INDEX

Explanations

look

np_max-act · gemini-2.0-flash

The neuron is highly sensitive to URL fragments—especially domain names and path components like “look.com” and the adjoining slash‐number tokens.

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

asis

-0.07

shape

-0.06

itamin

-0.06

msgs

-0.06

 нагруз

-0.06

inst

-0.06

aul

-0.06

haps

-0.06

sz

-0.06

pas

-0.06

POSITIVE LOGITS

look

0.08

WV

0.07

wa

0.07

Orn

0.06

'gc

0.06

orderId

0.06

Omn

0.06

精

0.06

WC

0.06

Nga

0.06

Activations Density 0.000%

look

The neuron is highly sensitive to URL fragments—especially domain names and path components like “look.com” and the adjoining slash‐number tokens.

No Comments

No Known Activations