© 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. 15-RESID-POST-AA
    11. 86515
    Prev
    Next
    INDEX
    Explanations

    project

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    聯
    -0.06
     Род
    -0.06
    FontOfSize
    -0.06
    换
    -0.06
    공부
    -0.06
    .histogram
    -0.06
     خی
    -0.06
    รรค
    -0.06
    Infrastructure
    -0.06
    Hour
    -0.06
    POSITIVE LOGITS
     smoothed
    0.06
    níky
    0.06
     support
    0.06
    -margin
    0.06
     domácí
    0.06
     supplying
    0.06
     tooltip
    0.06
    BB
    0.06
     paced
    0.06
     stresses
    0.06
    Activations Density 0.020%

    No Known Activations