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. 75894
    Prev
    Next
    INDEX
    Explanations

    quotes

    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
    자의
    -0.07
     ей
    -0.06
    κά
    -0.06
     veren
    -0.06
    cribing
    -0.06
    Authenticate
    -0.06
    isons
    -0.06
    ونه
    -0.06
    actice
    -0.06
    Shift
    -0.06
    POSITIVE LOGITS
    _due
    0.07
     finances
    0.07
     \↵
    0.06
    ucht
    0.06
     Reign
    0.06
    不可
    0.06
    (',
    0.06
     positively
    0.06
     İş
    0.06
     BBQ
    0.06
    Activations Density 0.006%

    No Known Activations