INDEX

Explanations

tapering/decreasing

np_max-act · gemini-2.0-flash

This neuron detects descriptive shape-or size-change terms—especially words indicating tapering or gradual variation (e.g. “tapered,” “narrower,” “decreasing,” “wider”).

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

展示

-0.06

activities

-0.06

=_

-0.06

 іс

-0.06

 meinem

-0.06

tot

-0.06

.gs

-0.06

fold

-0.06

Roman

-0.06

 seminal

-0.06

POSITIVE LOGITS

.layoutControlItem

0.07

ขว

0.07

-Dec

0.07

 Typed

0.07

 besar

0.06

_THEME

0.06

$image

0.06

))?

0.06

 Vega

0.06

-sama

0.06

Activations Density 0.031%

tapering/decreasing

This neuron detects descriptive shape-or size-change terms—especially words indicating tapering or gradual variation (e.g. “tapered,” “narrower,” “decreasing,” “wider”).

No Comments

No Known Activations

tapering/decreasing

This neuron detects descriptive shape-or size-change terms—especially words indicating tapering or gradual variation (e.g. “tapered,” “narrower,” “decreasing,” “wider”).

No Comments

No Known Activations