© 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. 22706
    Prev
    Next
    INDEX
    Explanations

    gene expression experiments

    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
     handling
    -0.07
    ucchini
    -0.07
     voluntary
    -0.06
    tics
    -0.06
     hoses
    -0.06
    _dist
    -0.06
     důvod
    -0.06
     circulating
    -0.06
     Jing
    -0.06
     výhod
    -0.05
    POSITIVE LOGITS
     können
    0.07
    stringValue
    0.07
     existed
    0.06
    	then
    0.06
     quen
    0.06
    ,
↵
    0.06
    .zone
    0.06
     Home
    0.06
    .daily
    0.06
    كية
    0.06
    Activations Density 0.026%

    No Known Activations