© 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 (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 106596
    Prev
    Next
    INDEX
    Explanations

    ::

    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
     knowledgeable
    -0.06
     Expand
    -0.06
     "{\"
    -0.06
    _ROLE
    -0.06
     unspecified
    -0.05
    diet
    -0.05
    MR
    -0.05
    _TYPEDEF
    -0.05
    領
    -0.05
    Italy
    -0.05
    POSITIVE LOGITS
    دة
    0.07
    ef
    0.07
     Session
    0.07
    цать
    0.06
    )];↵
    0.06
     выше
    0.06
    يرة
    0.06
    γων
    0.06
     اجرا
    0.06
    تف
    0.06
    Activations Density 0.005%

    No Known Activations