INDEX

Explanations

MIT

np_max-act · gemini-2.0-flash

mentions of copyright holders or authors associated with the MIT License.

oai_token-act-pair · gpt-4o-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

 схем

-0.07

 Thorn

-0.07

♀♀

-0.07

 Vert

-0.07

.Vert

-0.06

 },
↵
↵

-0.06

osomes

-0.06

 reimb

-0.06

.Mult

-0.06

 Belle

-0.06

POSITIVE LOGITS

MIT

0.10

知

0.07

 median

0.07

 skills

0.07

 correct

0.07

tip

0.07

FAIL

0.07

 poor

0.06

 Çin

0.06

Failed

0.06

Activations Density 0.002%

MIT

mentions of copyright holders or authors associated with the MIT License.

No Comments

No Known Activations