© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 91039
    Prev
    Next
    INDEX
    Explanations

    parallel arrangements

    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
    _TX
    -0.06
     irrit
    -0.06
    策
    -0.06
    esda
    -0.06
    inery
    -0.06
    biology
    -0.06
    enden
    -0.06
    ITIZE
    -0.06
    iang
    -0.06
    ntl
    -0.06
    POSITIVE LOGITS
    ,new
    0.07
     Awesome
    0.07
    股份
    0.06
    iểu
    0.06
     Great
    0.06
     brilliantly
    0.06
    coli
    0.06
     حرکت
    0.06
     الحديث
    0.06
    _AST
    0.06
    Activations Density 0.030%

    No Known Activations