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. 112938
    Prev
    Next
    INDEX
    Explanations

    /c

    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
     Υπο
    -0.06
    пат
    -0.06
     mass
    -0.06
     mont
    -0.06
     estos
    -0.06
     wann
    -0.06
    _Util
    -0.06
    Maintenance
    -0.06
    ="">
    ↵
    -0.06
     Avg
    -0.06
    POSITIVE LOGITS
     odpowied
    0.07
    esk
    0.07
    SmartPointer
    0.06
     odpově
    0.06
    ?q
    0.06
     Plaza
    0.06
    袖
    0.06
     вес
    0.06
    Formatting
    0.06
     lesbi
    0.06
    Activations Density 0.000%

    No Known Activations