© 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. 11-RESID-POST-AA
    11. 46692
    Prev
    Next
    INDEX
    Explanations

    People

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     혼
    -0.06
    =df
    -0.06
     Ranch
    -0.06
     conj
    -0.06
     variant
    -0.06
     Lazar
    -0.06
     Fix
    -0.06
     lhs
    -0.06
     nec
    -0.06
     vars
    -0.06
    POSITIVE LOGITS
     people
    0.20
     People
    0.19
    People
    0.19
    people
    0.17
     PEOPLE
    0.15
     الناس
    0.11
    OPLE
    0.11
    "People
    0.11
    .people
    0.10
     peoples
    0.10
    Activations Density 0.069%

    No Known Activations