© 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. 15-RESID-POST-AA
    6. 55827
    Prev
    Next
    INDEX
    Explanations

    art description

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prosecute
    -0.07
    ěstí
    -0.07
    Argentina
    -0.07
    MaxY
    -0.07
    _axes
    -0.06
    _requested
    -0.06
    omitempty
    -0.06
    ыл
    -0.06
     پا
    -0.06
    legalArgumentException
    -0.06
    POSITIVE LOGITS
    �
    0.06
    στα
    0.06
    σει
    0.06
     Δη
    0.06
     thor
    0.06
    fell
    0.06
     Chart
    0.06
    rien
    0.06
     ging
    0.06
    combo
    0.05
    Activations Density 0.149%

    No Known Activations