© 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. 11-RESID-POST-AA
    11. 51521
    Prev
    Next
    INDEX
    Explanations

    squadron

    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
     optimizations
    -0.07
    -debug
    -0.07
    INGTON
    -0.07
     paylaş
    -0.06
     vida
    -0.06
     tratt
    -0.06
     هر
    -0.06
     Poz
    -0.06
    ología
    -0.06
     서버
    -0.06
    POSITIVE LOGITS
    ────────
    0.06
    __(*
    0.06
    阻
    0.06
    :before
    0.06
    .lo
    0.06
    gro
    0.06
     Typeface
    0.06
    .final
    0.06
    ylie
    0.06
    _UNS
    0.06
    Activations Density 0.005%

    No Known Activations