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. 27-RESID-POST-AA
    6. 102182
    Prev
    Next
    INDEX
    Explanations

    Northamptonshire locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     closet
    -0.07
     neighborhood
    -0.07
    推荐
    -0.07
     USHORT
    -0.06
    boom
    -0.06
    Quotes
    -0.06
     textbook
    -0.06
    trimmed
    -0.06
     usuarios
    -0.06
     cartel
    -0.06
    POSITIVE LOGITS
     tego
    0.06
     firestore
    0.06
     kendisine
    0.06
     للإ
    0.06
     고개를
    0.06
     ⌒
    0.06
    -prev
    0.06
     />)↵
    0.06
     Hurricane
    0.06
    (ev
    0.05
    Activations Density 0.005%

    No Known Activations