INDEX

Explanations

as

np_max-act · gemini-2.0-flash

The neuron detects descriptive phrases of a chemical’s physical appearance or form (e.g. color, state, texture).

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

.Room

-0.07

_filt

-0.06

 Salt

-0.06

 він

-0.06

.shutdown

-0.06

.Window

-0.06

 departure

-0.06

.setting

-0.06

.Full

-0.06

ÜRK

-0.06

POSITIVE LOGITS

廊

0.07

pecia

0.07

肃

0.07

_^

0.07

ía

0.07

{_

0.07

 metallic

0.07

 ↵↵

0.06

isan

0.06

 Rahman

0.06

Activations Density 0.023%

as

The neuron detects descriptive phrases of a chemical’s physical appearance or form (e.g. color, state, texture).

No Comments

No Known Activations