INDEX

Explanations

``

np_max-act · gemini-2.0-flash

The neuron fires on occurrences of zlib compression/decompression function calls.

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

/****************************************

-0.09

 geld

-0.08

//@

-0.07

 Kentucky

-0.07

 Peters

-0.07

(P

-0.07

�

-0.07

몸

-0.07

*@

-0.07

VEN

-0.07

POSITIVE LOGITS

''

0.08

``(

0.08

''

0.07

.''

0.07

``

0.07

iar

0.06

NodeId

0.06

 Cliff

0.06

ursor

0.06

Activations Density 0.023%

``

The neuron fires on occurrences of zlib compression/decompression function calls.

No Comments

No Known Activations