© 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. 78603
    Prev
    Next
    INDEX
    Explanations

    /*

    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
    (typ
    -0.07
    辞
    -0.07
    -f
    -0.07
    ('_',
    -0.06
     torpedo
    -0.06
    庆
    -0.06
     Paypal
    -0.06
     ineff
    -0.06
     butterflies
    -0.06
     tumors
    -0.06
    POSITIVE LOGITS
     /*
    0.07
     Romeo
    0.07
    restrict
    0.06
    그래
    0.06
     NSUInteger
    0.06
     '\'
    0.06
     impacted
    0.05
    idUser
    0.05
    CharacterSet
    0.05
    狗
    0.05
    Activations Density 0.001%

    No Known Activations