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. 10582
    Prev
    Next
    INDEX
    Explanations

    events

    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
    ocio
    -0.06
     Reeves
    -0.06
     "'"
    -0.06
     आध
    -0.06
     Hungary
    -0.06
    不存在
    -0.06
     haf
    -0.06
     corrid
    -0.06
     CheckBox
    -0.06
    _memory
    -0.06
    POSITIVE LOGITS
    ,map
    0.06
    _PROP
    0.06
     ruthless
    0.06
     çöz
    0.06
     searchTerm
    0.06
    -android
    0.06
    Exporter
    0.06
    icolon
    0.06
     приб
    0.06
    gressive
    0.06
    Activations Density 0.000%

    No Known Activations