© 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. 70394
    Prev
    Next
    INDEX
    Explanations

    dream interpretation

    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
    ousedown
    -0.07
    ignum
    -0.07
    ляет
    -0.07
     trục
    -0.06
     bullying
    -0.06
    ул
    -0.06
    Foto
    -0.06
     dropped
    -0.06
    ิ
    -0.06
     Fleming
    -0.06
    POSITIVE LOGITS
     giàu
    0.07
    _REC
    0.07
    .robot
    0.06
    (argv
    0.06
     NIL
    0.06
     established
    0.06
    .site
    0.06
    weights
    0.06
     setup
    0.06
     Admin
    0.06
    Activations Density 0.011%

    No Known Activations