INDEX

Explanations

Disagreement, opinions

np_max-act · gemini-2.0-flash

This neuron detects speaker-role tokens (e.g., “Developer,” “Reviewer,” “developers,” “reviewers”) in the conversation.

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

 classNames

-0.07

.TabStop

-0.06

 매우

-0.06

	PreparedStatement

-0.06

_strength

-0.06

 felon

-0.06

	login

-0.06

 volleyball

-0.06

iar

-0.06

 ShoppingCart

-0.06

POSITIVE LOGITS

Nov

0.07

pike

0.06

 Orch

0.06

Sets

0.06

 avait

0.06

Rich

0.06

return

0.06

 rejection

0.06

Lock

0.06

产生

0.06

Activations Density 0.002%

Disagreement, opinions

This neuron detects speaker-role tokens (e.g., “Developer,” “Reviewer,” “developers,” “reviewers”) in the conversation.

No Comments

No Known Activations