© 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. 127176
    Prev
    Next
    INDEX
    Explanations

    URLs and references related to documentation or technical resources

    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
    231
    -0.06
    ille
    -0.06
    oller
    -0.06
    ndern
    -0.06
    /animations
    -0.06
    ugen
    -0.06
    ร
    -0.06
    ashtra
    -0.05
     austerity
    -0.05
    ani
    -0.05
    POSITIVE LOGITS
    getParameter
    0.08
     Gor
    0.08
    VERRIDE
    0.07
    ÅĽÄĩ
    0.07
    IfExists
    0.07
    OAD
    0.07
    ERING
    0.07
    .infinity
    0.07
    PropertyValue
    0.07
    Powered
    0.07
    Activations Density 0.000%

    No Known Activations