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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 28685
    Prev
    Next
    INDEX
    Explanations

    Relationships between things

    np_max-act · gemini-2.0-flash

    words and phrases that mark spatial relationships or specific locations (junctions, meeting/intersection points, or "where"/"at" clauses).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    greater
    -0.07
    ?
↵
    -0.06
     себ
    -0.06
    ､↵
    -0.06
     spelling
    -0.06
     {"
    -0.06
    ()}
    -0.06
     `
    -0.06
    ्द
    -0.06
    ############
    -0.06
    POSITIVE LOGITS
     Berlin
    0.07
    OptionsItemSelected
    0.07
     männ
    0.06
     ap
    0.06
     dział
    0.06
     الأ
    0.06
     FactoryGirl
    0.06
    LIKELY
    0.06
     радян
    0.06
    puties
    0.06
    Activations Density 0.024%

    No Known Activations