© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 70928
    Prev
    Next
    INDEX
    Explanations

    attacks

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JNIEnv
    -0.07
    alığı
    -0.07
    .WinControls
    -0.07
    <section
    -0.07
    .Emit
    -0.06
     BSP
    -0.06
     ду
    -0.06
     devlet
    -0.06
     bền
    -0.06
     hứ
    -0.06
    POSITIVE LOGITS
     equation
    0.07
     accessible
    0.07
     Cooler
    0.07
    qrt
    0.06
     Stroke
    0.06
    IVES
    0.06
     corporation
    0.06
     thriller
    0.06
    ornado
    0.06
     stroke
    0.06
    Activations Density 0.021%

    No Known Activations