© 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. 75955
    Prev
    Next
    INDEX
    Explanations

    references to spatial orientation and direction

    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
     zug
    -0.06
    edith
    -0.06
    587
    -0.06
    راد
    -0.06
     Sle
    -0.06
    adÃŃ
    -0.06
    raison
    -0.06
     existing
    -0.06
     ÑĢоз
    -0.05
    лам
    -0.05
    POSITIVE LOGITS
     screenSize
    0.07
    Äĵ
    0.06
    most
    0.06
    vens
    0.06
    rikes
    0.06
    å·¦åı³
    0.06
    -left
    0.06
    érieur
    0.06
    -sizing
    0.06
    forge
    0.06
    Activations Density 0.003%

    No Known Activations