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. 87041
    Prev
    Next
    INDEX
    Explanations

    receiving

    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
    عدد
    -0.06
    omm
    -0.06
    اوی
    -0.06
    جاد
    -0.06
    алось
    -0.06
    population
    -0.06
    ря
    -0.06
    .Detail
    -0.06
    ticker
    -0.06
    atum
    -0.06
    POSITIVE LOGITS
    ;break
    0.07
    !</
    0.07
     heal
    0.07
     insecurity
    0.07
    ]|
    0.07
     Or
    0.07
     inauguration
    0.06
    ,w
    0.06
     Car
    0.06
    ,key
    0.06
    Activations Density 0.000%

    No Known Activations