INDEX

Explanations

period tokens

np_max-act · gemini-2.0-flash

This neuron detects the “F.” reporter abbreviation in U.S. federal appellate case citations.

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

Altern

-0.07

respuesta

-0.07

 indir

-0.06

.repeat

-0.06

ko

-0.06

munition

-0.06

_helpers

-0.06

óa

-0.06

 k�

-0.06

_prepare

-0.06

POSITIVE LOGITS

0.07

ynn

0.07

NSArray

0.07

xFFFFFFFF

0.06

Tele

0.06

athy

0.06

ORMAT

0.06

"';↵

0.06

 tactile

0.06

Activations Density 0.001%

period tokens

This neuron detects the “F.” reporter abbreviation in U.S. federal appellate case citations.

No Comments

No Known Activations