© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 31965
    Prev
    Next
    INDEX
    Explanations

    days and times

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avel
    -0.07
     statue
    -0.07
     ropes
    -0.07
     street
    -0.06
    problems
    -0.06
    Angle
    -0.06
    Order
    -0.06
     books
    -0.06
    /us
    -0.06
    892
    -0.06
    POSITIVE LOGITS
    	So
    0.07
    	logger
    0.07
     وأن
    0.06
     Syrian
    0.06
     tốt
    0.06
    ponsored
    0.06
     în
    0.06
    olkien
    0.06
    .protobuf
    0.06
     multinational
    0.06
    Activations Density 0.018%

    No Known Activations