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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 123161
    Prev
    Next
    INDEX
    Explanations

    Dwellings

    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
     Cục
    -0.07
    izzes
    -0.06
    Cells
    -0.06
    Crime
    -0.06
    ldr
    -0.06
    /sn
    -0.06
    mates
    -0.06
    .Enc
    -0.06
    friends
    -0.05
     PROFILE
    -0.05
    POSITIVE LOGITS
     sorter
    0.07
     considers
    0.07
    場合は
    0.06
     [↵↵
    0.06
     ред
    0.06
    ,看
    0.06
     Branch
    0.06
     comprise
    0.06
    .Where
    0.06
    чаются
    0.06
    Activations Density 0.034%

    No Known Activations