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. 74028
    Prev
    Next
    INDEX
    Explanations

    But

    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
                    ↵                ↵
    -0.07
     استاندارد
    -0.07
     incoming
    -0.06
     contractor
    -0.06
     feedback
    -0.06
     fill
    -0.06
     Regression
    -0.06
     Integration
    -0.06
     Add
    -0.06
     Contractor
    -0.06
    POSITIVE LOGITS
    abile
    0.07
     BI
    0.07
     WT
    0.06
     elementType
    0.06
    ritable
    0.06
    ertation
    0.06
    957
    0.06
     Grande
    0.06
    ẻ
    0.06
     kad
    0.06
    Activations Density 0.000%

    No Known Activations