© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 93514
    Prev
    Next
    INDEX
    Explanations

    German possessive pronouns

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -0.08
    this
    -0.07
    .Active
    -0.07
    τώ
    -0.06
     atmos
    -0.06
    ativity
    -0.06
    _SCOPE
    -0.06
     Office
    -0.06
     مع
    -0.06
    _compat
    -0.06
    POSITIVE LOGITS
     ihre
    0.28
     seine
    0.23
     deine
    0.18
     Ihre
    0.15
     meine
    0.15
     unsere
    0.14
     seinen
    0.14
     ihren
    0.12
     seiner
    0.11
     meiner
    0.11
    Activations Density 0.008%

    No Known Activations