INDEX

Explanations

Legal cases

np_max-act · gemini-2.0-flash

The neuron predominantly activates on Westlaw‐style parallel citations (i.e. the “WL” token and its accompanying report 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mdl

-0.07

 tore

-0.07

:new

-0.07

ê

-0.07

benchmark

-0.07

,SLOT

-0.07

tus

-0.06

 spoiler

-0.06

 trips

-0.06

 stretching

-0.06

POSITIVE LOGITS

FO

0.07

lucent

0.07

/';↵↵

0.06

р

0.06

ζα

0.06

 Sega

0.06

others

0.06

Declaration

0.06

.dst

0.06

disciplinary

0.06

Activations Density 0.001%

Legal cases

The neuron predominantly activates on Westlaw‐style parallel citations (i.e. the “WL” token and its accompanying report numbers).

No Comments

No Known Activations