© 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. 39226
    Prev
    Next
    INDEX
    Explanations

    information related to awards and grant applications

    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
    _DIP
    -0.06
    opyright
    -0.06
    rana
    -0.06
    noc
    -0.06
    irt
    -0.06
    imedia
    -0.06
     ev
    -0.06
    arn
    -0.06
     Pending
    -0.06
    itor
    -0.06
    POSITIVE LOGITS
    ç»Ĩ
    0.07
     instructions
    0.07
     detailed
    0.07
     TEMPLATE
    0.07
     elim
    0.07
     instruction
    0.07
    announcement
    0.07
     hÆ°á»Ľng
    0.07
     ÑĤÑĢебованиÑı
    0.07
     criteria
    0.07
    Activations Density 0.024%

    No Known Activations