INDEX

Explanations

only

np_max-act · gemini-2.0-flash

The neuron fires on the limiting qualifier “only,” highlighting instances of that word.

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

 setLocation

-0.07

.AWS

-0.07

dden

-0.07

lining

-0.07

 Beta

-0.06

_OK

-0.06

top

-0.06

 Tonight

-0.06

พ

-0.06

lines

-0.06

POSITIVE LOGITS

_
↵
↵

0.07

 outright

0.06

aycast

0.06

 ortalama

0.06

_attachments

0.06

agues

0.06

 stál

0.06

 stocking

0.06

.↵↵↵

0.06

 тор

0.06

Activations Density 0.017%

only

The neuron fires on the limiting qualifier “only,” highlighting instances of that word.

No Comments

No Known Activations