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. 19-RESID-POST-AA
    6. 10294
    Prev
    Next
    INDEX
    Explanations

    philately

    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
    (begin
    -0.07
     rượu
    -0.07
    _known
    -0.07
    ры
    -0.07
     swiper
    -0.06
    аны
    -0.06
    esity
    -0.06
    fare
    -0.06
    accumulator
    -0.06
    anners
    -0.06
    POSITIVE LOGITS
    hood
    0.07
    \Services
    0.06
    memory
    0.06
     knocks
    0.06
     ΠΑΝ
    0.06
    ิ้
    0.06
    _ANT
    0.06
     It
    0.06
    복
    0.06
    Principal
    0.06
    Activations Density 0.004%

    No Known Activations