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. 27-RESID-POST-AA
    6. 103772
    Prev
    Next
    INDEX
    Explanations

    Founding Fathers/Revolution

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stroke
    -0.07
    .errorMessage
    -0.07
    م
    -0.06
     ende
    -0.06
     audio
    -0.06
    (queue
    -0.06
    -gun
    -0.06
    dings
    -0.06
    不得
    -0.06
     Survival
    -0.06
    POSITIVE LOGITS
     cinsel
    0.07
    )];
    ↵
    0.06
    ABSPATH
    0.06
    TouchUpInside
    0.06
    ChildScrollView
    0.06
    ]={↵
    0.06
     ---------------------------------------------------------------------------↵
    0.06
     temel
    0.06
     blackmail
    0.06
    voř
    0.06
    Activations Density 0.048%

    No Known Activations