Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 109307
    Prev
    Next
    INDEX
    Explanations

    et

    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
    ERSHEY
    -0.07
    出す
    -0.06
    商
    -0.06
     möchten
    -0.06
    ids
    -0.06
    IntArray
    -0.06
    (prod
    -0.06
     потрібно
    -0.06
    坡
    -0.06
    軍
    -0.06
    POSITIVE LOGITS
     grap
    0.07
     Duchess
    0.07
     critics
    0.07
    .doc
    0.07
     standby
    0.07
    tent
    0.06
    /grpc
    0.06
    unal
    0.06
     FML
    0.06
    Functions
    0.06
    Activations Density 0.002%

    No Known Activations