© 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. 15-RESID-POST-AA
    11. 4065
    Prev
    Next
    INDEX
    Explanations

    stops

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    に対
    -0.07
    察
    -0.07
    νού
    -0.06
    defined
    -0.06
     povin
    -0.06
    ringe
    -0.06
     anunci
    -0.06
     disobed
    -0.06
    に行
    -0.06
     حذ
    -0.06
    POSITIVE LOGITS
    ="
    0.07
     Parent
    0.06
    ='
    0.06
     Curtis
    0.06
     Pew
    0.06
    pw
    0.06
    kuk
    0.06
    sha
    0.06
    destination
    0.06
    那里
    0.06
    Activations Density 0.246%

    No Known Activations