© 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 EvalsExportsinterp-engineNEWAPI 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. 87736
    Prev
    Next
    INDEX
    Explanations

    harm

    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_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
    ouston
    -0.08
     Becky
    -0.07
    uele
    -0.07
    avig
    -0.07
     dependencies
    -0.06
    ervoir
    -0.06
    ILER
    -0.06
    ací
    -0.06
    wij
    -0.06
     going
    -0.06
    POSITIVE LOGITS
     harm
    0.13
     Harm
    0.09
     harmed
    0.08
    害
    0.08
     harming
    0.08
     harms
    0.07
     Pharm
    0.07
     harmful
    0.07
    (bitmap
    0.07
     Hart
    0.07
    Activations Density 0.018%

    No Known Activations