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. 87100
    Prev
    Next
    INDEX
    Explanations

    extradition

    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
    IPP
    -0.07
     Hook
    -0.07
     lettre
    -0.06
    capacity
    -0.06
     Cove
    -0.06
    Neg
    -0.06
    剣
    -0.06
     Kata
    -0.06
    pants
    -0.06
     görüş
    -0.06
    POSITIVE LOGITS
     extradition
    0.11
     extrad
    0.10
    (ListNode
    0.07
    _Params
    0.07
     initialState
    0.07
    ğu
    0.07
    EventData
    0.07
    resultado
    0.07
     progresses
    0.06
    ітет
    0.06
    Activations Density 0.001%

    No Known Activations