© 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. 19-RESID-POST-AA
    11. 110753
    Prev
    Next
    INDEX
    Explanations

    =

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WRAPPER
    -0.07
     ({
    -0.06
    528
    -0.06
    isOpen
    -0.06
     duct
    -0.06
    <byte
    -0.06
    Syn
    -0.06
    721
    -0.06
    Decrypt
    -0.06
    ै।↵
    -0.06
    POSITIVE LOGITS
     yılda
    0.07
     disable
    0.07
    perfect
    0.06
    ��
    0.06
     donner
    0.06
    .hist
    0.06
    γκα
    0.06
    languages
    0.06
    phem
    0.06
     urban
    0.06
    Activations Density 0.035%

    No Known Activations