© 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. 7-RESID-POST-AA
    11. 6552
    Prev
    Next
    INDEX
    Explanations

    DynamoDB

    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
     swapping
    -0.06
     在
    -0.06
    792
    -0.06
     галузі
    -0.06
     mug
    -0.06
     kéo
    -0.06
     steroid
    -0.06
     공개
    -0.05
    ーマ
    -0.05
     моз
    -0.05
    POSITIVE LOGITS
    ynamodb
    0.07
     Dynamo
    0.07
     Shim
    0.07
     перем
    0.07
    ctl
    0.07
    різ
    0.07
     Basement
    0.07
    Lİ
    0.07
    _TextChanged
    0.07
    aminer
    0.07
    Activations Density 0.004%

    No Known Activations