© 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. 41184
    Prev
    Next
    INDEX
    Explanations

    terms related to research structure and citation

    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
    åī²
    -0.07
    окон
    -0.07
    rang
    -0.07
    /cms
    -0.07
    oÅĻ
    -0.07
    .createObject
    -0.07
    ushed
    -0.07
     Sle
    -0.07
    velte
    -0.07
    inge
    -0.07
    POSITIVE LOGITS
     conv
    0.08
     meteor
    0.07
    ç«ľ
    0.06
     Weather
    0.06
     forecast
    0.06
     hPa
    0.06
     ATM
    0.06
     Labrador
    0.06
     Meteor
    0.06
    _budget
    0.06
    Activations Density 0.040%

    No Known Activations