INDEX

Explanations

code

np_max-act · gemini-2.0-flash

The neuron is tuned to detect code identifiers—especially snake_case keys and keywords in code arrays or declarations.

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

current

-0.06

(now

-0.06

 roof

-0.06

PMC

-0.06

 rivalry

-0.06

usuarios

-0.06

.msg

-0.06

Various

-0.06

.sha

-0.06

’all

-0.06

POSITIVE LOGITS

 diminish

0.06

 итог

0.06

евого

0.06

 Peru

0.06

mět

0.06

ıda

0.06

 ayrı

0.06

ía

0.06

طبيق

0.06

ρθρο

0.06

Activations Density 0.088%

code

The neuron is tuned to detect code identifiers—especially snake_case keys and keywords in code arrays or declarations.

No Comments

No Known Activations