INDEX

Explanations

code and technical discussions

np_max-act · gemini-2.0-flash

Explanation of neuron 4 behavior: the main thing this neuron does is find occurrences of the C++ standard‐library “placeholders” identifier (as in std::placeholders).

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

_operand

-0.07

การพ

-0.07

_bed

-0.06

noe

-0.06

梯

-0.06

蜜

-0.06

.GetKey

-0.06

modified

-0.06

/text

-0.06

#ifdef

-0.06

POSITIVE LOGITS

 taken

0.08

 findViewById

0.07

�

0.07

frauen

0.07

 solic

0.07

(interface

0.07

 Aggregate

0.07

 Literary

0.06

言

0.06

่อย

0.06

Activations Density 0.000%

code and technical discussions

Explanation of neuron 4 behavior: the main thing this neuron does is find occurrences of the C++ standard‐library “placeholders” identifier (as in std::placeholders).

No Comments

No Known Activations