© 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. 11-RESID-POST-AA
    6. 17897
    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getProperty
    -0.07
    765
    -0.06
    _play
    -0.06
     UNIX
    -0.06
     मश
    -0.06
     translation
    -0.06
     currentPlayer
    -0.06
    electric
    -0.06
    power
    -0.06
     Steve
    -0.06
    POSITIVE LOGITS
    。当
    0.07
    FREE
    0.07
     TG
    0.07
    лишком
    0.06
    由于
    0.06
     titre
    0.06
    +l
    0.06
     Bloody
    0.06
     Assumes
    0.06
     tarafından
    0.06
    Activations Density 0.083%

    No Known Activations