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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 11302
    Prev
    Next
    INDEX
    Explanations

    references to restaurant reservations and dining logistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edin
    -0.17
     ware
    -0.14
    .Orientation
    -0.14
    elig
    -0.14
    ÑĢÑĥÑģ
    -0.14
     FETCH
    -0.13
    amburger
    -0.13
    ilip
    -0.13
    fresh
    -0.13
    zan
    -0.13
    POSITIVE LOGITS
     reservation
    0.55
     Reservation
    0.51
     reservations
    0.51
     booking
    0.47
    reservation
    0.43
    Reservation
    0.42
     bookings
    0.40
     Booking
    0.40
     reserv
    0.39
    booking
    0.39
    Activations Density 0.181%

    No Known Activations