© 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 EvalsExportsAPI 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. 99710
    Prev
    Next
    INDEX
    Explanations

    ，

    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
    アン
    -0.07
    illian
    -0.07
    fk
    -0.07
    <th
    -0.06
     annihil
    -0.06
     вним
    -0.06
     هناك
    -0.06
     nodded
    -0.06
    istically
    -0.06
     ajust
    -0.06
    POSITIVE LOGITS
    InBackground
    0.07
    이다
    0.06
     문서
    0.06
    _task
    0.06
     Latitude
    0.06
    나
    0.06
     nemus
    0.06
     waiver
    0.06
     màu
    0.06
    togroup
    0.06
    Activations Density 0.049%

    No Known Activations