© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 18495
    Prev
    Next
    INDEX
    Explanations

    the

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     embodiments
    -0.06
     natives
    -0.06
     ö
    -0.06
     제공
    -0.06
     méthode
    -0.06
     học
    -0.06
     selfies
    -0.06
    кувати
    -0.06
    oday
    -0.06
    ním
    -0.06
    POSITIVE LOGITS
    ْف
    0.07
    [val
    0.07
     담
    0.06
    _IMETHOD
    0.06
    .getPassword
    0.06
    ﾉ
    0.06
    нівер
    0.06
    :@
    0.06
    ，当
    0.06
    playlist
    0.06
    Activations Density 0.062%

    No Known Activations