© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 100142
    Prev
    Next
    INDEX
    Explanations

    heat

    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
     utens
    -0.07
    �부
    -0.07
    .large
    -0.06
     rightly
    -0.06
    ickerView
    -0.06
     Werk
    -0.06
     worldly
    -0.06
     olduk
    -0.06
     objet
    -0.06
     خدمات
    -0.06
    POSITIVE LOGITS
    normalized
    0.07
    До
    0.07
     %{
    0.06
    Headers
    0.06
     Optional
    0.06
    jà
    0.06
    Advanced
    0.06
    _param
    0.06
    cpp
    0.06
    ชม
    0.06
    Activations Density 0.001%

    No Known Activations