© 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. 7-RESID-POST-AA
    6. 94904
    Prev
    Next
    INDEX
    Explanations

    Name

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ैठ
    -0.07
    GetProcAddress
    -0.06
     воно
    -0.06
    чик
    -0.06
    partners
    -0.06
    fest
    -0.06
    _AREA
    -0.06
    enk
    -0.06
    ,nil
    -0.06
    921
    -0.06
    POSITIVE LOGITS
     exceptions
    0.07
    pecially
    0.07
     defended
    0.06
     Alias
    0.06
    ımızı
    0.06
    .hover
    0.06
     experimenting
    0.06
     durable
    0.06
    otypes
    0.06
     opt
    0.06
    Activations Density 0.025%

    No Known Activations