© 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. 27-RESID-POST-AA
    11. 36717
    Prev
    Next
    INDEX
    Explanations

    US locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contemplated
    -0.07
     potion
    -0.06
     signaled
    -0.06
    犯
    -0.06
    	level
    -0.06
     --------
    -0.06
    ládá
    -0.06
    af
    -0.06
    ifix
    -0.06
     activities
    -0.06
    POSITIVE LOGITS
     修
    0.07
     Russo
    0.07
     OnCollision
    0.07
    River
    0.07
     wyst
    0.06
     kodu
    0.06
     ar
    0.06
     InvalidOperationException
    0.06
     Yankees
    0.06
     этой
    0.06
    Activations Density 0.012%

    No Known Activations