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. 11-RESID-POST-AA
    6. 100411
    Prev
    Next
    INDEX
    Explanations

    short-lived

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AJ
    -0.07
    uracion
    -0.07
    ”的
    -0.07
    .When
    -0.07
     Curry
    -0.06
     Darkness
    -0.06
     Centro
    -0.06
     податков
    -0.06
     lumin
    -0.06
    ็จพระ
    -0.06
    POSITIVE LOGITS
    nave
    0.07
     protect
    0.07
    _LIGHT
    0.07
    .feature
    0.06
     timetable
    0.06
     compliments
    0.06
     household
    0.06
    (master
    0.06
    comment
    0.06
     measurements
    0.06
    Activations Density 0.016%

    No Known Activations