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. 90850
    Prev
    Next
    INDEX
    Explanations

    question marks and periods

    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
     Parr
    -0.07
     filles
    -0.06
     Muk
    -0.06
    NAS
    -0.06
    _ter
    -0.06
     BOOK
    -0.06
    Notify
    -0.06
     Foster
    -0.06
    buie
    -0.06
    _et
    -0.06
    POSITIVE LOGITS
    ัดส
    0.07
     */↵
    0.06
    (data
    0.06
    ?>
    ↵
    0.06
     виб
    0.06
     Disp
    0.06
    ////////
    0.06
     //--------------------------------
    0.06
    '/>↵
    0.06
    ()?
    0.06
    Activations Density 0.026%

    No Known Activations