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. 87036
    Prev
    Next
    INDEX
    Explanations

    breathing

    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
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fat
    -0.07
     Nex
    -0.06
    _tuple
    -0.06
     Projectile
    -0.06
    _CLIP
    -0.06
    "},{"
    -0.06
     AV
    -0.06
     звер
    -0.06
    غن
    -0.06
    uitka
    -0.06
    POSITIVE LOGITS
    ább
    0.07
    _INTERNAL
    0.06
     BEST
    0.06
    '&&
    0.06
    (board
    0.06
    USES
    0.06
     hardships
    0.06
     parl
    0.05
    enerating
    0.05
    512
    0.05
    Activations Density 0.008%

    No Known Activations