INDEX

Explanations

programming advice

np_max-act · gemini-2.0-flash

The neuron detects strongly opinionated or persuasive language—especially emphatic advice or urging expressions.

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

Şu

-0.06

 Мас

-0.06

 läng

-0.06

-zone

-0.06

 Mickey

-0.06

 bilir

-0.06

otionEvent

-0.06

 факти

-0.06

кого

-0.06

HasForeignKey

-0.06

POSITIVE LOGITS

0.08

CELL

0.07

tokens

0.07

nun

0.06

asures

0.06

Factors

0.06

ubes

0.06

 tokens

0.06

(can

0.06

Activations Density 0.060%

programming advice

The neuron detects strongly opinionated or persuasive language—especially emphatic advice or urging expressions.

No Comments

No Known Activations

programming advice

The neuron detects strongly opinionated or persuasive language—especially emphatic advice or urging expressions.

No Comments

No Known Activations