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. 92695
    Prev
    Next
    INDEX
    Explanations

    Currency

    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
    Deletes
    -0.08
    ENTICATION
    -0.07
     cathedral
    -0.07
     Huntington
    -0.07
    луш
    -0.06
    (IC
    -0.06
     Territory
    -0.06
    _Delete
    -0.06
    CTest
    -0.06
     uluslararası
    -0.06
    POSITIVE LOGITS
    áct
    0.06
    →→
    0.06
     exactly
    0.06
    سم
    0.06
     pár
    0.06
    parseInt
    0.06
    -reported
    0.06
    Completion
    0.06
     �
    0.05
    �
    0.05
    Activations Density 0.012%

    No Known Activations