© 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. 94095
    Prev
    Next
    INDEX
    Explanations

    research results

    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
    +n
    -0.07
    RI
    -0.06
    ิร
    -0.06
     Pref
    -0.06
    +p
    -0.06
    ρων
    -0.06
     Haupt
    -0.06
    .herokuapp
    -0.06
    维
    -0.06
    ingleton
    -0.06
    POSITIVE LOGITS
    ...,
    0.07
     Interior
    0.07
     result
    0.07
     morally
    0.07
    Friendly
    0.07
    (Stack
    0.07
     nga
    0.07
    loha
    0.06
     -->↵↵↵
    0.06
     trusted
    0.06
    Activations Density 0.071%

    No Known Activations