Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9320
    Prev
    Next
    INDEX
    Explanations

    Jay

    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
     whales
    -0.07
    abstract
    -0.06
    녕하세요
    -0.06
    ी।↵
    -0.06
     TypeInfo
    -0.06
    /info
    -0.06
     ebp
    -0.06
    -selection
    -0.06
     August
    -0.06
     More
    -0.05
    POSITIVE LOGITS
     Jay
    0.08
    SEA
    0.08
    INARY
    0.07
     Enlight
    0.07
    Jay
    0.07
    _alive
    0.07
    MemoryWarning
    0.07
    +c
    0.07
    evin
    0.07
     observable
    0.06
    Activations Density 0.002%

    No Known Activations