© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 19885
    Prev
    Next
    INDEX
    Explanations

    in

    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
    realDonaldTrump
    -0.07
    .Com
    -0.06
     bö
    -0.06
    _parameter
    -0.06
     cus
    -0.06
    ROUP
    -0.06
     KUR
    -0.06
    吹
    -0.06
     petroleum
    -0.06
    (classes
    -0.06
    POSITIVE LOGITS
     Scheduled
    0.07
    层
    0.07
     Loves
    0.07
     Boutique
    0.07
    SB
    0.06
     Comparable
    0.06
     рекомен
    0.06
     provoked
    0.06
     Guns
    0.06
    hes
    0.06
    Activations Density 0.054%

    No Known Activations