INDEX

Explanations

music albums

np_max-act · gemini-2.0-flash

This neuron fires on words that begin new sentences or section‐lead statements (e.g. “It,” “The,” “In,” etc.).

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

↵    ↵    ↵

-0.07

れる

-0.06

 Shin

-0.06

 knees

-0.06

_IO

-0.06

 lần

-0.06

딸

-0.06

oren

-0.06

 south

-0.06

ff

-0.06

POSITIVE LOGITS

 Pause

0.08

.BorderFactory

0.07

_PARTITION

0.07

animal

0.06

 weave

0.06

 Primitive

0.06

.ByteString

0.06

erged

0.06

.currentTarget

0.06

 territorial

0.06

Activations Density 0.073%

music albums

This neuron fires on words that begin new sentences or section‐lead statements (e.g. “It,” “The,” “In,” etc.).

No Comments

No Known Activations