INDEX

Explanations

this

np_max-act · gemini-2.0-flash

The neuron flags the question‐mark punctuation (the “?” tokens) in the text.

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

	fail

-0.07

.gb

-0.07

mb

-0.07

Instruction

-0.07

 زی

-0.06

 Jenn

-0.06

 toplantı

-0.06

StreamWriter

-0.06

-Life

-0.06

nd

-0.06

POSITIVE LOGITS

】↵

0.07

 hardships

0.07

 branching

0.07

 discourse

0.06

 epid

0.06

得到

0.06

(gameObject

0.06

 MORE

0.06

Detalle

0.06

 initialState

0.06

Activations Density 0.034%

this

The neuron flags the question‐mark punctuation (the “?” tokens) in the text.

No Comments

No Known Activations