INDEX

Explanations

n

np_max-act · gemini-2.0-flash

This neuron activates on string escape sequences for newlines (i.e. “\n”) in code literals.

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

 authors

-0.08

 ArgumentOutOfRangeException

-0.07

 exploration

-0.07

.setEmail

-0.07

OBS

-0.06

 servers

-0.06

.Attributes

-0.06

されている

-0.06

される

-0.06

 швидко

-0.06

POSITIVE LOGITS

uel

0.07

↵

0.07

�

0.06

Ћ

0.06

'${

0.06

�

0.06

vision

0.06

([[

0.06

 gesture

0.06

ской

0.06

Activations Density 0.006%

n

This neuron activates on string escape sequences for newlines (i.e. “\n”) in code literals.

No Comments

No Known Activations

n

This neuron activates on string escape sequences for newlines (i.e. “\n”) in code literals.

No Comments

No Known Activations