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. 101282
    Prev
    Next
    INDEX
    Explanations

    fan

    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
     crosses
    -0.07
    ,在
    -0.06
     Premier
    -0.06
     usleep
    -0.06
     peppers
    -0.06
     curved
    -0.06
    tractor
    -0.06
     Purs
    -0.06
     hå
    -0.06
     teamed
    -0.06
    POSITIVE LOGITS
    �
    0.07
     hành
    0.06
    /REC
    0.06
    alim
    0.06
    life
    0.06
    )</
    0.06
    扣
    0.06
     نسخه
    0.06
    yyy
    0.06
    heure
    0.06
    Activations Density 0.017%

    No Known Activations