© 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. 127492
    Prev
    Next
    INDEX
    Explanations

    patient

    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
     '.'
    -0.07
     prestigious
    -0.07
    statuses
    -0.07
    ازد
    -0.06
     bột
    -0.06
     Statements
    -0.06
    \"></
    -0.06
    703
    -0.06
    ず
    -0.06
     Одна
    -0.06
    POSITIVE LOGITS
     entren
    0.07
    .usermodel
    0.07
    .getOrElse
    0.07
    _ue
    0.06
    ,url
    0.06
    ubble
    0.06
    ornment
    0.06
     yerde
    0.06
    rowser
    0.06
    <Box
    0.06
    Activations Density 0.033%

    No Known Activations