INDEX

Explanations

You

np_max-act · gemini-2.0-flash

This neuron responds to relatively longer content words (tokens of about five or more characters), highlighting them with nonzero activations.

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

IEL

-0.07

 LEGO

-0.07

openid

-0.06

 FOUR

-0.06

viv

-0.06

�

-0.06

Cars

-0.06

�

-0.06

 Moist

-0.06

ग

-0.06

POSITIVE LOGITS

 turnovers

0.07

	post

0.06

 freezing

0.06

ilded

0.06

ackBar

0.06

Prim

0.06

unused

0.06

(Time

0.06

 Expires

0.05

献

0.05

Activations Density 0.299%

You

This neuron responds to relatively longer content words (tokens of about five or more characters), highlighting them with nonzero activations.

No Comments

No Known Activations

You

This neuron responds to relatively longer content words (tokens of about five or more characters), highlighting them with nonzero activations.

No Comments

No Known Activations