© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 45181
    Prev
    Next
    INDEX
    Explanations

    mixed, random text

    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
    841
    -0.06
     fractures
    -0.06
    icmp
    -0.06
     disposable
    -0.06
     eligibility
    -0.06
     scared
    -0.06
    습
    -0.06
    Battery
    -0.06
    ND
    -0.06
     Conflict
    -0.06
    POSITIVE LOGITS
    .b
    0.07
    ских
    0.07
     поступ
    0.06
    .QLabel
    0.06
    .da
    0.06
    をか
    0.06
     mansion
    0.06
     Magnum
    0.06
    ्दर
    0.06
    zeń
    0.06
    Activations Density 0.095%

    No Known Activations