© 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. 21206
    Prev
    Next
    INDEX
    Explanations

    commas and parenthesis

    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
     قل
    -0.07
    
    -0.07
     projeto
    -0.07
    โค
    -0.07
    彩票
    -0.07
     polarity
    -0.06
     бал
    -0.06
     potion
    -0.06
    
    -0.06
    —which
    -0.06
    POSITIVE LOGITS
     Apt
    0.07
    Qualified
    0.06
    _levels
    0.06
    .Dot
    0.06
     unfit
    0.06
    _Text
    0.06
    _dtype
    0.06
     Fucking
    0.06
    existent
    0.06
    .addRow
    0.06
    Activations Density 0.009%

    No Known Activations