© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 60398
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    Usuario
    -0.06
     Financing
    -0.06
    naires
    -0.06
     o
    -0.06
    embali
    -0.06
     refrigerator
    -0.06
     poorest
    -0.06
     ignoring
    -0.06
     млн
    -0.06
    據
    -0.06
    POSITIVE LOGITS
    Mahon
    0.07
     lieutenant
    0.07
    _WEAPON
    0.07
     Abbey
    0.07
     ดาว
    0.06
    FETCH
    0.06
     Luca
    0.06
    ="">
↵
    0.06
    Про
    0.06
     Werner
    0.06
    Activations Density 0.012%

    No Known Activations