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. 103622
    Prev
    Next
    INDEX
    Explanations

    say "annotation"

    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
     recounted
    -0.07
    ندق
    -0.07
     рук
    -0.06
    景
    -0.06
     disclosed
    -0.06
     resourceId
    -0.06
    Uno
    -0.06
     reinterpret
    -0.06
     Tribunal
    -0.06
    Tips
    -0.06
    POSITIVE LOGITS
    sam
    0.06
    ******
    0.06
    ARAM
    0.06
    SACTION
    0.06
    ENE
    0.06
    fsp
    0.06
    verage
    0.06
     багатьох
    0.06
     biomedical
    0.06
     benefici
    0.06
    Activations Density 0.048%

    No Known Activations