© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 114369
    Prev
    Next
    INDEX
    Explanations

    orch

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adidas
    -0.06
    cence
    -0.06
    .mul
    -0.06
     Suzuki
    -0.06
     Затем
    -0.06
     Harper
    -0.06
    Slave
    -0.05
     siblings
    -0.05
     Uno
    -0.05
     gef
    -0.05
    POSITIVE LOGITS
    -conscious
    0.07
     Koch
    0.07
     참고
    0.07
     PROC
    0.07
    ороз
    0.07
     useContext
    0.07
     Teach
    0.07
     energies
    0.07
     uch
    0.06
    PROCESS
    0.06
    Activations Density 0.003%

    No Known Activations