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. 111413
    Prev
    Next
    INDEX
    Explanations

    people

    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
     indications
    -0.08
    .orange
    -0.08
    .group
    -0.07
    στα
    -0.07
    __*/
    -0.06
     Mart
    -0.06
     STORE
    -0.06
     motors
    -0.06
     optionally
    -0.06
     camps
    -0.06
    POSITIVE LOGITS
    Selectable
    0.07
     Eudicots
    0.07
    ?↵
    0.07
     Reporter
    0.06
    -'
    0.06
     :
    ↵
    0.06
    udo
    0.06
     Imper
    0.06
    raisal
    0.06
    _macro
    0.06
    Activations Density 0.021%

    No Known Activations