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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 99173
    Prev
    Next
    INDEX
    Explanations

    v

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     please
    -0.07
     输出
    -0.06
     reduced
    -0.06
     Guang
    -0.06
     icon
    -0.06
    添
    -0.06
    (火
    -0.06
    	tab
    -0.06
     metall
    -0.06
    瑞
    -0.06
    POSITIVE LOGITS
    าส
    0.08
     автомати
    0.08
    */)
    0.07
    tım
    0.07
     kimse
    0.06
     робот
    0.06
    tura
    0.06
    texture
    0.06
    PHA
    0.06
    folios
    0.06
    Activations Density 0.003%

    No Known Activations