Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 34215
    Prev
    Next
    INDEX
    Explanations

    Unformatted text/code

    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
    .Produ
    -0.07
     HEAD
    -0.06
     Triumph
    -0.06
     Produ
    -0.06
     mana
    -0.06
     MED
    -0.06
    warf
    -0.06
    .valor
    -0.06
     WINDOWS
    -0.06
     Translator
    -0.06
    POSITIVE LOGITS
    jon
    0.07
     policies
    0.07
    lb
    0.06
     TN
    0.06
     четвер
    0.06
     опис
    0.06
    лия
    0.06
    ío
    0.06
    exact
    0.06
     boards
    0.06
    Activations Density 0.000%

    No Known Activations