Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 74870
    Prev
    Next
    INDEX
    Explanations

    cup

    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
    Behind
    -0.07
     beast
    -0.07
     backtrack
    -0.07
    _big
    -0.07
     NO
    -0.07
     Beyond
    -0.07
    genre
    -0.07
     Reagan
    -0.07
    _not
    -0.07
    ān
    -0.07
    POSITIVE LOGITS
     cup
    0.15
     Cup
    0.14
     cups
    0.13
     Cups
    0.10
    up
    0.08
    um
    0.08
     Mug
    0.08
    cup
    0.08
     куп
    0.07
    UP
    0.07
    Activations Density 0.013%

    No Known Activations