INDEX

Explanations

numbers and measurements

np_max-act · gemini-2.0-flash

The neuron fires on numeric tokens showing decimal or fractional values (i.e. floating-point numbers).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

":[

-0.07

 message

-0.07

.sender

-0.07

 Stark

-0.07

，其中

-0.07

Night

-0.07

 Platinum

-0.06

.cast

-0.06

.Schedule

-0.06

.Maximum

-0.06

POSITIVE LOGITS

ASM

0.06

 لع

0.06

 lạc

0.06

 iets

0.06

ABA

0.06

-meta

0.06

 TERMS

0.06

php

0.06

pard

0.06

resse

0.06

Activations Density 0.144%

numbers and measurements

The neuron fires on numeric tokens showing decimal or fractional values (i.e. floating-point numbers).

No Comments

No Known Activations