© 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 EvalsExportsinterp-engineNEWAPI 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. 92886
    Prev
    Next
    INDEX
    Explanations

    references to companies and their services related to entertainment technology

    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
     apr
    -0.06
    rain
    -0.06
    äm
    -0.05
     Sud
    -0.05
     onItemClick
    -0.05
     rainbow
    -0.05
    asta
    -0.05
     Maur
    -0.05
    ãģĦãģĨ
    -0.05
    asto
    -0.05
    POSITIVE LOGITS
    weetalert
    0.08
    аÑĢам
    0.08
    ukan
    0.08
    ãĤ¾
    0.07
    utterstock
    0.07
    _SDK
    0.07
    _sdk
    0.07
    anson
    0.07
     seat
    0.07
    ТÐŀ
    0.07
    Activations Density 0.005%

    No Known Activations