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. 19-RESID-POST-AA
    6. 83561
    Prev
    Next
    INDEX
    Explanations

    administrative actions, assurance, engagement

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qi
    -0.07
    rack
    -0.06
     عشر
    -0.06
     '_'
    -0.06
    Alarm
    -0.06
    rive
    -0.06
    Leod
    -0.06
    嘴
    -0.06
     Thy
    -0.06
    Thin
    -0.06
    POSITIVE LOGITS
    <translation
    0.07
     prejud
    0.07
    (sec
    0.07
    (cluster
    0.06
     Dire
    0.06
     controvers
    0.06
    .ForegroundColor
    0.06
    :"-"`↵
    0.06
    pcion
    0.06
    _Desc
    0.06
    Activations Density 0.069%

    No Known Activations