INDEX

Explanations

will

np_max-act · gemini-2.0-flash

This neuron detects occurrences of the auxiliary “will,” marking statements of future intent or planned actions.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 له

-0.06

 pinch

-0.06

(""))

-0.06

pow

-0.06

Pause

-0.06

)})

-0.06

Execution

-0.06

 Operand

-0.06

POSITIVE LOGITS

athlete

0.06

 Slovakia

0.06

iov

0.06

 рахунок

0.06

_BLUE

0.06

 üniversit

0.06

 Hong

0.06

 verdiği

0.06

考

0.06

Activations Density 0.018%

will

This neuron detects occurrences of the auxiliary “will,” marking statements of future intent or planned actions.

No Comments

No Known Activations