INDEX

Explanations

factual statements

np_max-act · gemini-2.0-flash

information related to specific software tools and platforms.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

This neuron never activates—it doesn’t detect any particular text pattern.

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

_checkpoint

-0.06

-port

-0.06

 additions

-0.06

Israeli

-0.06

 recipient

-0.06

โท

-0.06

_sets

-0.06

Rank

-0.06

 national

-0.06

efon

-0.06

POSITIVE LOGITS

Coy

0.06

 RegexOptions

0.06

literal

0.06

HY

0.06

(userid

0.06

ibrated

0.06

|"

0.06

 khắc

0.06

_bo

0.06

 đai

0.06

Activations Density 0.028%

factual statements

information related to specific software tools and platforms.

This neuron never activates—it doesn’t detect any particular text pattern.

No Comments

No Known Activations