INDEX

Explanations

Apologizing or explaining

np_max-act · gemini-2.0-flash

This neuron does not respond to any tokens and thus does not detect any specific pattern.

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

VERBOSE

-0.07

Ｍ

-0.07

ERNEL

-0.06

็บไซต

-0.06

_pow

-0.06

gh

-0.06

inicio

-0.06

 พฤศจ

-0.06

paginator

-0.06

 grease

-0.06

POSITIVE LOGITS

ripe

0.06

_PROVIDER

0.06

_FLAGS

0.06

 toss

0.06

 Instit

0.06

.LoggerFactory

0.06

 Photo

0.06

.route

0.06

该

0.06

[ch

0.06

Activations Density 0.036%

Apologizing or explaining

This neuron does not respond to any tokens and thus does not detect any specific pattern.

No Comments

No Known Activations