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

    Neuronpedia

    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. 94518
    Prev
    Next
    INDEX
    Explanations

    terms related to digital media and security in the context of gaming and property management

    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
    _mA
    -0.08
     shorthand
    -0.07
    enson
    -0.07
     famil
    -0.06
    nav
    -0.06
    gem
    -0.06
     بÙĢ
    -0.06
     undermin
    -0.06
    祥
    -0.06
     cele
    -0.06
    POSITIVE LOGITS
     Tato
    0.07
    Ñĩи
    0.07
    ujÄħ
    0.07
     Opr
    0.07
     equipments
    0.06
    rani
    0.06
    ÃŃses
    0.06
     wise
    0.06
    manship
    0.06
    cis
    0.06
    Activations Density 0.296%

    No Known Activations