© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52660
    Prev
    Next
    INDEX
    Explanations

    are

    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
     tuner
    -0.07
     Fusion
    -0.07
    .Calendar
    -0.07
     projectiles
    -0.06
     helpless
    -0.06
    (pol
    -0.06
     Kurum
    -0.06
     Boehner
    -0.06
    Lookup
    -0.06
     observer
    -0.06
    POSITIVE LOGITS
     Uruguay
    0.07
    асти
    0.06
    dal
    0.06
    áct
    0.06
    ối
    0.06
    ляти
    0.06
    民
    0.06
     гем
    0.06
    必要
    0.06
    assage
    0.06
    Activations Density 0.025%

    No Known Activations