© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44170
    Prev
    Next
    INDEX
    Explanations

    brainstorm/storm

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is spot mentions of creative‐thinking or brainstorming activities (e.g. brainstorming, idea generation, mind mapping).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    .mix
    -0.06
    età
    -0.06
     порядок
    -0.06
     "";
↵
↵
    -0.06
     calcul
    -0.06
    蛋
    -0.06
    adığ
    -0.06
    azioni
    -0.06
    .tipo
    -0.06
    itic
    -0.06
    POSITIVE LOGITS
     brainstorm
    0.11
     Coron
    0.07
     Nebraska
    0.07
    rief
    0.06
    fer
    0.06
     dispos
    0.06
     Disney
    0.06
     Ide
    0.06
    .Business
    0.06
    ja
    0.06
    Activations Density 0.005%

    No Known Activations