INDEX

Explanations

code

np_max-act · gemini-2.0-flash

The neuron is responding to numeric tokens that contain decimal points (i.e. floating‐point literals).

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

 Sparks

-0.07

ingo

-0.07

 Engineering

-0.07

 популяр

-0.07

ukes

-0.07

-gradient

-0.07

ynchronized

-0.07

Hibernate

-0.07

_minutes

-0.07

.visitVarInsn

-0.06

POSITIVE LOGITS

 thể

0.07

 scientifically

0.06

्ठ

0.06

.Pod

0.06

(List

0.06

なの

0.06

 vara

0.06

(outputs

0.06

 brit

0.06

divid

0.06

Activations Density 0.040%

code

The neuron is responding to numeric tokens that contain decimal points (i.e. floating‐point literals).

No Comments

No Known Activations