© 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. 27972
    Prev
    Next
    INDEX
    Explanations

    margin

    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
    写
    -0.07
    _hello
    -0.07
     POP
    -0.07
     boats
    -0.06
     erotic
    -0.06
    例如
    -0.06
     Deutsche
    -0.06
    _foot
    -0.06
     compar
    -0.06
     reproductive
    -0.06
    POSITIVE LOGITS
     margin
    0.11
     Margin
    0.09
    	margin
    0.09
     margins
    0.09
     Mason
    0.08
    Margin
    0.08
     Carson
    0.08
    ions
    0.08
     Ramp
    0.07
     Morgan
    0.07
    Activations Density 0.008%

    No Known Activations