INDEX

Explanations

examined

np_max-act · gemini-2.0-flash

The main thing this neuron does is find mentions of method validation or testing—verbs and phrases that report experimental evaluation or examination of an approach.

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

 infer

-0.06

earn

-0.06

	cancel

-0.06

INC

-0.06

_reward

-0.06

 hypotheses

-0.06

 villains

-0.06

haps

-0.06

efault

-0.06

yok

-0.06

POSITIVE LOGITS

 PropertyChanged

0.06

λικά

0.06

ancements

0.06

디시

0.06

кет

0.06

ención

0.06

\Field

0.06

ACHI

0.06

}";↵

0.06

 textile

0.06

Activations Density 0.028%

examined

The main thing this neuron does is find mentions of method validation or testing—verbs and phrases that report experimental evaluation or examination of an approach.

No Comments

No Known Activations