© 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 EvalsExportsinterp-engineNEWAPI 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. 93708
    Prev
    Next
    INDEX
    Explanations

    dend

    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
     srv
    -0.08
    ique
    -0.07
    丶
    -0.07
    .prob
    -0.07
     Raq
    -0.07
     suchen
    -0.07
    warz
    -0.07
    iani
    -0.07
     respect
    -0.06
    uator
    -0.06
    POSITIVE LOGITS
     dend
    0.12
     ""));↵
    0.07
     datings
    0.06
    INavigation
    0.06
     subrange
    0.06
     setFrame
    0.06
     چنان
    0.06
    514
    0.06
    .setColumns
    0.06
     CLIIIK
    0.06
    Activations Density 0.001%

    No Known Activations