© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29098
    Prev
    Next
    INDEX
    Explanations

    references to availability and limits on places and seating

    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
    ksi
    -0.07
    oldt
    -0.07
    rani
    -0.07
    ึà¸ģ
    -0.06
    ogan
    -0.06
    kova
    -0.06
    enheim
    -0.06
    oha
    -0.06
    oola
    -0.06
    orr
    -0.06
    POSITIVE LOGITS
     reserved
    0.10
    reserved
    0.09
     available
    0.08
     coveted
    0.07
     availability
    0.07
     RESERVED
    0.07
    ets
    0.07
     reserv
    0.07
     Reserved
    0.07
     ten
    0.07
    Activations Density 0.020%

    No Known Activations