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

    Neuronpedia

    APICircuit 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. 11-RESID-POST-AA
    6. 104215
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     passes
    -0.07
     wheel
    -0.06
     bob
    -0.06
     nursing
    -0.06
     nurs
    -0.06
     Abbey
    -0.06
    靠
    -0.06
    .ImageView
    -0.06
    .decrypt
    -0.06
    avaş
    -0.06
    POSITIVE LOGITS
     Оп
    0.06
    [mid
    0.06
    THR
    0.06
    CLLocation
    0.06
     يق
    0.06
     ORM
    0.06
    _WORDS
    0.06
    (plan
    0.06
    .XRLabel
    0.06
    OldData
    0.06
    Activations Density 0.012%

    No Known Activations