© 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. 24127
    Prev
    Next
    INDEX
    Explanations

    intended

    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
     importantes
    -0.07
     So
    -0.06
    .Photo
    -0.06
    ポ
    -0.06
    YSQL
    -0.06
     нескольких
    -0.06
     �
    -0.06
    lov
    -0.06
     researched
    -0.06
    不是
    -0.06
    POSITIVE LOGITS
     intended
    0.19
     unintended
    0.10
     intends
    0.08
     intend
    0.07
     Nottingham
    0.07
     destin
    0.07
     interim
    0.07
     destined
    0.07
     Tillerson
    0.07
     Quentin
    0.07
    Activations Density 0.008%

    No Known Activations