INDEX

Explanations

text excerpts

np_max-act · gemini-2.0-flash

The neuron mainly lights up on common English function words—especially short prepositions and articles (“in,” “the,” “for,” “when,” etc.)—marking the connective scaffolding of sentences.

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

 sometimes

-0.06

iples

-0.06

igr

-0.06

캐

-0.06

(Max

-0.06

 notebooks

-0.06

 initiation

-0.05

byt

-0.05

浪

-0.05

POSITIVE LOGITS

 hodnoty

0.07

 đích

0.07

	Start

0.07

dim

0.06

 roman

0.06

ierten

0.06

 producto

0.06

按钮

0.06

 camb

0.06

-bars

0.06

Activations Density 0.111%

text excerpts

The neuron mainly lights up on common English function words—especially short prepositions and articles (“in,” “the,” “for,” “when,” etc.)—marking the connective scaffolding of sentences.

No Comments

No Known Activations