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. 15-RESID-POST-AA
    6. 121288
    Prev
    Next
    INDEX
    Explanations

    is

    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
     frail
    -0.07
    鎮
    -0.06
     Mothers
    -0.06
    导致
    -0.06
    ываются
    -0.06
     guilty
    -0.06
     Af
    -0.06
     klu
    -0.06
     borderBottom
    -0.06
    duction
    -0.06
    POSITIVE LOGITS
     Tolkien
    0.06
    око
    0.06
    504
    0.06
    elp
    0.06
    еліг
    0.06
     archetype
    0.06
    ');↵↵
    0.06
     ta
    0.06
    (optional
    0.06
    ]',
    0.06
    Activations Density 0.001%

    No Known Activations