© 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. 22755
    Prev
    Next
    INDEX
    Explanations

    Scientific and Technical phrases.Method: 4, scientific and technical phrases

    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
    운드
    -0.07
     interv
    -0.07
     их
    -0.07
    userData
    -0.06
    -ม
    -0.06
     survey
    -0.06
     physic
    -0.06
    Teams
    -0.06
     нач
    -0.06
    Singapore
    -0.06
    POSITIVE LOGITS
    .jboss
    0.06
     thor
    0.06
    /projects
    0.06
     sens
    0.06
     maxX
    0.06
     classy
    0.06
     hiểm
    0.06
    lexible
    0.06
    limitations
    0.06
    (clazz
    0.05
    Activations Density 0.106%

    No Known Activations