© 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 EvalsExportsAPI 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. 11147
    Prev
    Next
    INDEX
    Explanations

    optimal

    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
     user
    -0.06
     backyard
    -0.06
     beside
    -0.06
    Mais
    -0.06
     ++;↵
    -0.06
    (worker
    -0.06
     warehouses
    -0.06
     war
    -0.06
    	click
    -0.06
    weeney
    -0.06
    POSITIVE LOGITS
    Opt
    0.09
     optimal
    0.08
     Optim
    0.08
    optim
    0.08
     CPS
    0.08
    Appro
    0.08
     otp
    0.07
    OPT
    0.07
     OPT
    0.07
    計
    0.07
    Activations Density 0.009%

    No Known Activations