Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 127377
    Prev
    Next
    INDEX
    Explanations

    Something is wrong/incorrect

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /datatables
    -0.07
    рами
    -0.07
     ты
    -0.07
    /dd
    -0.07
     i
    -0.07
     Antony
    -0.07
     filed
    -0.06
    ()."
    -0.06
     prostitution
    -0.06
    cono
    -0.06
    POSITIVE LOGITS
     wallets
    0.07
     lows
    0.06
    :host
    0.06
    venting
    0.06
     vents
    0.06
    ]);
    ↵
    0.06
     exceptions
    0.06
     갤로그로
    0.06
    _PROCESS
    0.06
     Une
    0.06
    Activations Density 0.131%

    No Known Activations