© 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. 15-RESID-POST-AA
    6. 99602
    Prev
    Next
    INDEX
    Explanations

    categories

    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
     Johnson
    -0.08
     Hansen
    -0.08
     vet
    -0.07
     Temple
    -0.07
    During
    -0.07
     Fiction
    -0.07
    ;↵
    -0.07
     Crazy
    -0.07
    Дата
    -0.07
     Comprehensive
    -0.07
    POSITIVE LOGITS
    Feels
    0.06
    ــــــــ
    0.06
     envi
    0.06
    _train
    0.06
    .oper
    0.06
    \FrameworkBundle
    0.06
    _runs
    0.05
    OCI
    0.05
    силь
    0.05
     musel
    0.05
    Activations Density 0.026%

    No Known Activations