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. 21338
    Prev
    Next
    INDEX
    Explanations

    is

    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
     bureauc
    -0.08
    Work
    -0.07
     Experience
    -0.07
     Harding
    -0.06
     Weed
    -0.06
     derechos
    -0.06
     guerr
    -0.06
     Fragen
    -0.06
     Clearance
    -0.06
     zůst
    -0.06
    POSITIVE LOGITS
    _colour
    0.06
     [][]
    0.06
    Э
    0.06
     адрес
    0.06
    _resp
    0.06
     datap
    0.06
    _objs
    0.06
     Magnum
    0.05
    :len
    0.05
    _major
    0.05
    Activations Density 0.000%

    No Known Activations