© 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. 27-RESID-POST-AA
    11. 92686
    Prev
    Next
    INDEX
    Explanations

    microscopy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kültür
    -0.07
    Greek
    -0.07
     shields
    -0.07
    -strip
    -0.07
     harassed
    -0.07
     sandwich
    -0.06
     funktion
    -0.06
     Yu
    -0.06
     detection
    -0.06
    February
    -0.06
    POSITIVE LOGITS
     рис
    0.06
    亭
    0.06
     существует
    0.06
    aders
    0.06
     آنها
    0.05
     раб
    0.05
    Segue
    0.05
     aks
    0.05
    _or
    0.05
    演
    0.05
    Activations Density 0.012%

    No Known Activations