INDEX

Explanations

length

np_max-act · gemini-2.0-flash

The neuron consistently lights up on tokens naming or computing buffer/string lengths (e.g. variables like “buf”, “Len”, “msg_len” and related numeric size expressions).

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

，您

-0.07

 Destiny

-0.06

").

-0.06

 дод

-0.06

USTER

-0.06

_HALF

-0.06

structions

-0.06

 Slot

-0.06

-do

-0.05

dition

-0.05

POSITIVE LOGITS

datetime

0.07

 ServletException

0.07

 日本

0.07

 minim

0.07

 Authorized

0.07

Bai

0.06

_bytes

0.06

ในส

0.06

 dispose

0.06

Shr

0.06

Activations Density 0.005%

length

The neuron consistently lights up on tokens naming or computing buffer/string lengths (e.g. variables like “buf”, “Len”, “msg_len” and related numeric size expressions).

No Comments

No Known Activations