© 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. 15-RESID-POST-AA
    11. 34184
    Prev
    Next
    INDEX
    Explanations

    biology, science

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suspect
    -0.07
    ادت
    -0.07
     бур
    -0.07
     covered
    -0.06
    よ
    -0.06
     rob
    -0.06
     permit
    -0.06
     cover
    -0.06
     Implementation
    -0.06
     rigor
    -0.06
    POSITIVE LOGITS
    brace
    0.07
    هـ
    0.07
     CGRectMake
    0.07
    .DeepEqual
    0.06
    

↵
    0.06
    ::<
    0.06
    arrings
    0.06
    picture
    0.06
     Downing
    0.06
    手机
    0.06
    Activations Density 0.353%

    No Known Activations