Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 94213
    Prev
    Next
    INDEX
    Explanations

    chemical compounds

    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
    "One
    -0.06
     slows
    -0.06
     slow
    -0.06
     seldom
    -0.06
     varies
    -0.06
     Thought
    -0.06
    ソン
    -0.06
    予
    -0.06
    ging
    -0.06
    ขนาด
    -0.06
    POSITIVE LOGITS
    ());
    ↵
    ↵
    0.07
     ناح
    0.07
     breaches
    0.07
    _AES
    0.06
    '){
    ↵
    0.06
    ]){
    0.06
     Jou
    0.06
     gridBagConstraints
    0.06
     вой
    0.06
     simd
    0.06
    Activations Density 0.034%

    No Known Activations