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. 15-RESID-POST-AA
    6. 53253
    Prev
    Next
    INDEX
    Explanations

    technical processes

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存档备份
    -0.07
     mời
    -0.06
     funkci
    -0.06
    昭和
    -0.06
     /\.
    -0.06
     싸
    -0.06
     عاما
    -0.06
     رق
    -0.06
     restructuring
    -0.06
     当
    -0.06
    POSITIVE LOGITS
     releasing
    0.06
     Merge
    0.06
    оне
    0.06
    umn
    0.06
     swinging
    0.06
     '{
    0.06
    ниц
    0.06
    Obj
    0.06
     Los
    0.06
    bool
    0.06
    Activations Density 0.269%

    No Known Activations