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. 31048
    Prev
    Next
    INDEX
    Explanations

    programming 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
    ,is
    -0.07
    ("&
    -0.06
     отношения
    -0.06
     Fault
    -0.06
    .assertIn
    -0.06
     RelayCommand
    -0.06
    ways
    -0.06
    Cách
    -0.06
    }\.[
    -0.06
    _clients
    -0.06
    POSITIVE LOGITS
    �
    0.07
     внеш
    0.07
    	vo
    0.06
    ations
    0.06
     γλώ
    0.06
    irtual
    0.06
    PAGE
    0.06
     асп
    0.06
    hest
    0.06
    ाभ
    0.06
    Activations Density 0.034%

    No Known Activations