© 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. 73743
    Prev
    Next
    INDEX
    Explanations

    negative descriptions

    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
     rift
    -0.06
     visibly
    -0.06
     simply
    -0.06
     comprised
    -0.06
     factions
    -0.06
    =create
    -0.06
     tour
    -0.06
     Following
    -0.06
     arrive
    -0.06
     люб
    -0.06
    POSITIVE LOGITS
    prm
    0.07
    mage
    0.06
     hend
    0.06
    asmine
    0.06
    _DISPLAY
    0.06
     인간
    0.06
     what
    0.06
     erotica
    0.06
    ivre
    0.06
    culate
    0.06
    Activations Density 0.012%

    No Known Activations