© 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. 119959
    Prev
    Next
    INDEX
    Explanations

    Abbreviations/Identifiers

    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
    Acknowled
    -0.07
     athletic
    -0.06
    inu
    -0.06
     �
    -0.06
    eno
    -0.06
     Vũ
    -0.06
     Rx
    -0.06
    tm
    -0.06
     filmer
    -0.06
     bicycles
    -0.06
    POSITIVE LOGITS
    --}}↵
    0.07
     近
    0.06
     Most
    0.06
    ım
    0.06
     SPR
    0.06
     عدم
    0.06
    akest
    0.06
    ertype
    0.06
    ;';↵
    0.06
    .`);↵
    0.06
    Activations Density 1.429%

    No Known Activations