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. 30913
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    итив
    -0.06
     puss
    -0.06
    ocê
    -0.06
    چ
    -0.06
    /moment
    -0.06
    öy
    -0.06
     Ко
    -0.06
    타
    -0.06
    들도
    -0.06
    Pos
    -0.06
    POSITIVE LOGITS
     crunchy
    0.07
    /fonts
    0.06
    命周期
    0.06
    .Linked
    0.06
    .rate
    0.06
     Skate
    0.06
    .QRect
    0.06
    (NAME
    0.06
    puted
    0.06
     Instead
    0.06
    Activations Density 0.004%

    No Known Activations