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. 52854
    Prev
    Next
    INDEX
    Explanations

    code

    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
    Adjusted
    -0.07
    IQUE
    -0.06
     Replies
    -0.06
    jít
    -0.06
    ้า
    -0.06
     clue
    -0.06
    ourcem
    -0.06
     Sof
    -0.06
    ซ
    -0.06
     بسیار
    -0.06
    POSITIVE LOGITS
    .seconds
    0.07
    motion
    0.07
    _RC
    0.07
     captains
    0.07
     socks
    0.06
     середови
    0.06
    _GC
    0.06
     executive
    0.06
     investments
    0.06
    ามารถ
    0.06
    Activations Density 0.013%

    No Known Activations