© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 27824
    Prev
    Next
    INDEX
    Explanations

    situation

    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
     bleiben
    -0.07
    eam
    -0.06
     abortion
    -0.06
     взаєм
    -0.06
     après
    -0.06
     capabilities
    -0.06
     LIN
    -0.06
     khi
    -0.06
    inned
    -0.06
     centro
    -0.06
    POSITIVE LOGITS
    -components
    0.07
    ковой
    0.07
    小
    0.07
     GS
    0.06
    ज़
    0.06
     {:
    0.06
    foods
    0.06
     Stability
    0.06
    ической
    0.06
     contends
    0.06
    Activations Density 0.001%

    No Known Activations