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. 9713
    Prev
    Next
    INDEX
    Explanations

    example

    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
    ValueGenerationStrategy
    -0.07
    textTheme
    -0.06
     abilities
    -0.06
    (ns
    -0.06
     kullanılan
    -0.06
     سابق
    -0.06
    __,
    -0.06
     gebruik
    -0.06
    $max
    -0.06
    //----------------------------------------------------------------------------↵
    -0.06
    POSITIVE LOGITS
     appointment
    0.07
     xứ
    0.07
    CODE
    0.07
    dem
    0.06
     proyectos
    0.06
     exceedingly
    0.06
     dance
    0.06
     neph
    0.06
    knowledge
    0.06
     impedance
    0.06
    Activations Density 0.000%

    No Known Activations