© 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. 27853
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    ढ़
    -0.07
     funct
    -0.06
     Snap
    -0.06
    ulan
    -0.06
    应
    -0.06
    wor
    -0.06
    Lost
    -0.06
     uyar
    -0.06
     χαρα
    -0.06
     рук
    -0.06
    POSITIVE LOGITS
    tro
    0.06
     luaL
    0.06
    \Builder
    0.06
     Member
    0.06
    +-+-+-+-
    0.06
    ESCO
    0.06
     designation
    0.06
    Cells
    0.06
    _COMM
    0.06
     playerName
    0.06
    Activations Density 0.053%

    No Known Activations