INDEX

Explanations

Information Technology

np_max-act · gemini-2.0-flash

The neuron activates on mentions of software tools, libraries, frameworks, and platforms used in development (e.g., programming languages, web frameworks, game engines, and visualization tools).

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

Negative Logits

 watering

-0.07

есь

-0.06

-confidence

-0.06

 chef

-0.06

-key

-0.06

therapy

-0.06

-related

-0.06

 system

-0.06

ुआ

-0.06

POSITIVE LOGITS

:]↵↵

0.08

************************

0.07

BIT

0.07

Ό

0.07

>;
↵

0.07

ADD

0.07

 [↵↵

0.06

.
↵
↵

0.06

 pige

0.06

:])↵

0.06

Activations Density 0.090%

Information Technology

The neuron activates on mentions of software tools, libraries, frameworks, and platforms used in development (e.g., programming languages, web frameworks, game engines, and visualization tools).

No Known Activations

Information Technology

The neuron activates on mentions of software tools, libraries, frameworks, and platforms used in development (e.g., programming languages, web frameworks, game engines, and visualization tools).

No Known Activations