© 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. 87455
    Prev
    Next
    INDEX
    Explanations

    magnets

    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
     modify
    -0.07
    СР
    -0.07
     amigos
    -0.07
    courses
    -0.06
     reviewers
    -0.06
     ホ
    -0.06
    lien
    -0.06
     GAP
    -0.06
    ']];↵
    -0.06
    ENCES
    -0.06
    POSITIVE LOGITS
    _MOUNT
    0.07
    ))/
    0.06
    (util
    0.06
    stellung
    0.06
     dönüş
    0.06
     bv
    0.06
     DataManager
    0.06
     poster
    0.06
     علم
    0.06
     PV
    0.06
    Activations Density 0.017%

    No Known Activations