© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 52293
    Prev
    Next
    INDEX
    Explanations

    them

    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
     enacted
    -0.07
    ा।↵↵
    -0.07
    ereotype
    -0.06
    '>↵↵
    -0.06
    >>↵↵
    -0.06
    _Struct
    -0.06
    uebas
    -0.06
     whitelist
    -0.06
    '>
    ↵
    -0.06
     blamed
    -0.06
    POSITIVE LOGITS
     ημέ
    0.07
    λικά
    0.06
    Pass
    0.06
     situace
    0.06
     así
    0.06
     entirely
    0.06
     upgrade
    0.06
     hugely
    0.06
    smart
    0.06
     cardiac
    0.06
    Activations Density 0.024%

    No Known Activations