© 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 EvalsExportsinterp-engineNEWAPI 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. 93817
    Prev
    Next
    INDEX
    Explanations

    akes

    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
    회사
    -0.07
    	win
    -0.07
    _processor
    -0.07
    -bound
    -0.06
    .Audio
    -0.06
     sqlSession
    -0.06
     rapide
    -0.06
    wallet
    -0.06
    	stop
    -0.06
     füh
    -0.06
    POSITIVE LOGITS
    /d
    0.06
    Writable
    0.06
    '];?></
    0.06
    akes
    0.06
    rocessing
    0.06
     tasty
    0.06
     Horse
    0.06
    acos
    0.06
     [\
    0.06
     horse
    0.06
    Activations Density 0.001%

    No Known Activations