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. 87080
    Prev
    Next
    INDEX
    Explanations

    from

    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
    _lcd
    -0.07
    칙
    -0.07
     intends
    -0.06
    ardless
    -0.06
     crypto
    -0.06
     rumor
    -0.06
    _async
    -0.06
     nearby
    -0.06
    aleigh
    -0.06
    (latitude
    -0.06
    POSITIVE LOGITS
     SZ
    0.08
    Ren
    0.07
    A
    0.07
     upgraded
    0.07
    轉
    0.06
    尊
    0.06
    反
    0.06
    зя
    0.06
    Reject
    0.06
    isz
    0.06
    Activations Density 0.019%

    No Known Activations