Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 29274
    Prev
    Next
    INDEX
    Explanations

    recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ideals
    -0.06
    بد
    -0.06
     triples
    -0.06
    全部
    -0.06
    иск
    -0.06
     coefficients
    -0.06
    Employee
    -0.06
    	widget
    -0.06
     когда
    -0.06
    _lost
    -0.06
    POSITIVE LOGITS
     peel
    0.06
     голови
    0.06
    óg
    0.06
    .liferay
    0.06
    YE
    0.06
     poj
    0.06
     emiss
    0.06
    .Void
    0.06
    ریز
    0.06
     Rutgers
    0.06
    Activations Density 0.065%

    No Known Activations