INDEX

Explanations

ladder

np_max-act · gemini-2.0-flash

references to ladders in various contexts or applications.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

The neuron responds to occurrences of the word “ladder” (mentions of ladders or related ladder devices).

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

qp

-0.07

iants

-0.06

onces

-0.06

.places

-0.06

Ron

-0.06

 Shows

-0.06

ong

-0.06

 nổi

-0.06

cribe

-0.06

estado

-0.06

POSITIVE LOGITS

 ladder

0.14

adders

0.08

梯

0.07

�

0.07

 timeline

0.07

retty

0.07

 accr

0.07

––

0.07

_tree

0.07

adr

0.07

Activations Density 0.001%

ladder

references to ladders in various contexts or applications.

The neuron responds to occurrences of the word “ladder” (mentions of ladders or related ladder devices).

No Comments

No Known Activations