© 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. 19-RESID-POST-AA
    6. 29531
    Prev
    Next
    INDEX
    Explanations

    insect life cycles

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resisted
    -0.06
    BUM
    -0.06
    Uber
    -0.06
     Dynamics
    -0.06
    احة
    -0.06
     Tabs
    -0.06
    WORDS
    -0.06
     peas
    -0.06
    ATED
    -0.06
    остей
    -0.06
    POSITIVE LOGITS
    _POS
    0.07
     orderBy
    0.06
    alloca
    0.06
     getActivity
    0.06
    printf
    0.06
     материалов
    0.06
     practical
    0.06
     кош
    0.06
     مشهد
    0.06
    .writeString
    0.06
    Activations Density 0.012%

    No Known Activations