© 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. 7-RESID-POST-AA
    6. 97533
    Prev
    Next
    INDEX
    Explanations

    only

    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
     �
    -0.06
     hecho
    -0.06
    ią
    -0.06
    ocht
    -0.06
    cpf
    -0.06
    elop
    -0.06
    =k
    -0.06
    ehler
    -0.06
     reports
    -0.06
    OAD
    -0.06
    POSITIVE LOGITS
     only
    0.07
     Pelosi
    0.07
     Only
    0.07
     guint
    0.06
     massa
    0.06
    DUCT
    0.06
    価
    0.06
    -sizing
    0.06
     فقط
    0.06
     reordered
    0.06
    Activations Density 0.004%

    No Known Activations