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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 103656
    Prev
    Next
    INDEX
    Explanations

    contract agreements

    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
     nutné
    -0.06
     juin
    -0.06
     reven
    -0.06
    ourt
    -0.06
    _has
    -0.06
    projects
    -0.06
    esz
    -0.06
    ,$
    -0.06
    birthdate
    -0.06
    _execution
    -0.06
    POSITIVE LOGITS
     Multiple
    0.07
     قتل
    0.07
    Multiple
    0.07
     arsenal
    0.07
     chilling
    0.06
     noisy
    0.06
     воспал
    0.06
     Concurrent
    0.06
     classic
    0.06
     location
    0.06
    Activations Density 0.011%

    No Known Activations