© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 63000
    Prev
    Next
    INDEX
    Explanations

    expressions related to the availability and provision of information and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patri
    -0.07
    Ø·ÙĨ
    -0.06
    PickerController
    -0.06
    rios
    -0.06
    NullOrEmpty
    -0.06
    edList
    -0.06
     Nab
    -0.06
    ноÑģи
    -0.06
     Lep
    -0.05
    zen
    -0.05
    POSITIVE LOGITS
     available
    0.13
     AVAILABLE
    0.11
     availability
    0.11
    available
    0.11
     unavailable
    0.10
     disponibles
    0.10
    -available
    0.10
    vailable
    0.10
     Available
    0.10
     disponible
    0.10
    Activations Density 0.072%

    No Known Activations