© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 70956
    Prev
    Next
    INDEX
    Explanations

    Tampering

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ما
    -0.07
     fatally
    -0.06
    =====↵
    -0.06
    그
    -0.06
     الذهاب
    -0.06
     Der
    -0.06
    ประว
    -0.06
    .Namespace
    -0.06
    network
    -0.06
    ～↵↵
    -0.06
    POSITIVE LOGITS
    uspended
    0.06
     treadmill
    0.06
     çıktı
    0.06
    ポ
    0.06
     côt
    0.06
     concerts
    0.06
     babel
    0.06
    uable
    0.06
     spyOn
    0.06
    Drawable
    0.06
    Activations Density 0.135%

    No Known Activations