INDEX

Explanations

code

np_max-act · gemini-2.0-flash

code or script artifacts associated with licensing and copyright information.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.Items

-0.08

arr

-0.06

Employ

-0.06

_resource

-0.06

菜

-0.06

Hor

-0.06

 Sites

-0.06

election

-0.06

 franc

-0.06

pow

-0.06

POSITIVE LOGITS

_BASIC

0.06

obec

0.06

.Lerp

0.06

 VIDEO

0.06

止

0.06

<Tuple

0.06

�i

0.06

，便

0.06

 getPosition

0.06

 vzděl

0.06

Activations Density 0.043%

code

code or script artifacts associated with licensing and copyright information.

No Comments

No Known Activations