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. 24749
    Prev
    Next
    INDEX
    Explanations

    strong

    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
    parts
    -0.07
    .lower
    -0.07
     pirates
    -0.07
     nếu
    -0.07
     altar
    -0.07
    시키
    -0.06
     NotFound
    -0.06
    UnderTest
    -0.06
    idad
    -0.06
     TOTAL
    -0.06
    POSITIVE LOGITS
     tool
    0.07
    لیل
    0.07
     رشته
    0.06
    Rare
    0.06
    _IMM
    0.06
     brochure
    0.06
    yer
    0.06
     чемпіон
    0.06
    letal
    0.06
    ternal
    0.06
    Activations Density 0.001%

    No Known Activations