© 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
    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. 27415
    Prev
    Next
    INDEX
    Explanations

    Instructions and information

    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
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pixar
    -0.07
     RedirectToAction
    -0.07
    「
    -0.06
    あ
    -0.06
     Eğitim
    -0.06
    	git
    -0.06
     ziy
    -0.06
     enviar
    -0.06
    .notifications
    -0.06
    152
    -0.06
    POSITIVE LOGITS
    --;
    0.07
    high
    0.07
    HF
    0.06
     FOUR
    0.06
    /YYYY
    0.06
    .singleton
    0.06
    .addProperty
    0.06
     olmadığını
    0.06
    urities
    0.06
    tracted
    0.06
    Activations Density 0.137%

    No Known Activations