INDEX

Explanations

programming/data analysis

np_max-act · gemini-2.0-flash

This neuron never activates (all activation values are zero), so it does not detect any token patterns.

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

.monitor

-0.07

.SuppressLint

-0.06

td

-0.06

rips

-0.06

 адміністратив

-0.06

ponce

-0.06

ソ

-0.05

..."

-0.05

.fa

-0.05

opes

-0.05

POSITIVE LOGITS

 Αγ

0.08

-->

0.07

 earth

0.07

 etraf

0.06

最初

0.06

 bere

0.06

_FULL

0.06

 Rifle

0.06

และส

0.06

Activations Density 0.010%

programming/data analysis

This neuron never activates (all activation values are zero), so it does not detect any token patterns.

No Comments

No Known Activations

programming/data analysis

This neuron never activates (all activation values are zero), so it does not detect any token patterns.

No Comments

No Known Activations