INDEX

Explanations

__

np_max-act · gemini-2.0-flash

The neuron detects sequences of underscores used as divider lines or formatting separators in legal‐document headers.

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

avi

-0.07

Sanders

-0.07

.node

-0.06

 Nachricht

-0.06

="/">

-0.06

 prolific

-0.06

 DISCLAIM

-0.06

.collect

-0.06

::::::

-0.06

.depart

-0.06

POSITIVE LOGITS

tion

0.07

 sympathetic

0.06

fusion

0.06

_OUTPUT

0.06

ioni

0.06

 Foley

0.06

atm

0.06

$"

0.06

量

0.06

Activations Density 0.002%

__

The neuron detects sequences of underscores used as divider lines or formatting separators in legal‐document headers.

No Comments

No Known Activations

__

The neuron detects sequences of underscores used as divider lines or formatting separators in legal‐document headers.

No Comments

No Known Activations