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

    Neuronpedia

    Jacobian LensNEW
    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. 27-RESID-POST-AA
    11. 19008
    Prev
    Next
    INDEX
    Explanations

    angry/curse words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    節
    -0.07
    iddle
    -0.07
    Comparator
    -0.07
    _SELF
    -0.06
    打开
    -0.06
     superficial
    -0.06
    LOY
    -0.06
    acle
    -0.06
    ovými
    -0.06
    rello
    -0.06
    POSITIVE LOGITS
     دیده
    0.06
    %E
    0.06
    ornecedor
    0.06
    -management
    0.06
    EventManager
    0.06
     Proceed
    0.06
     dag
    0.06
    ンタ
    0.06
     Seconds
    0.06
    rové
    0.06
    Activations Density 0.096%

    No Known Activations