INDEX

Explanations

numbers

np_max-act · gemini-2.0-flash

The neuron fires on any token that denotes a number or numeric type in code—e.g. numeric literals (like “100” or “0.264892578125”), data‐type labels (“Integer”), or words like “number”/“número.”

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

code snippets related to mathematical operations and potential errors in user inputs.

oai_token-act-pair · gpt-4o-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

 نار

-0.07

TECTED

-0.07

_func

-0.07

.Token

-0.06

�y

-0.06

_calls

-0.06

_caps

-0.06

�

-0.06

Bindings

-0.06

VERY

-0.06

POSITIVE LOGITS

$array

0.07

kola

0.06

 UITextField

0.06

δ

0.06

 Institution

0.06

####

0.06

�

0.06

 Refer

0.06

 Aaron

0.06

Activations Density 0.018%

numbers

The neuron fires on any token that denotes a number or numeric type in code—e.g. numeric literals (like “100” or “0.264892578125”), data‐type labels (“Integer”), or words like “number”/“número.”

code snippets related to mathematical operations and potential errors in user inputs.

No Comments

No Known Activations