© 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. 108048
    Prev
    Next
    INDEX
    Explanations

    references to budgetary amounts and contract-related information

    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
    ekil
    -0.06
    uria
    -0.06
    asser
    -0.06
    tal
    -0.06
    uers
    -0.06
     Tu
    -0.06
     ά
    -0.06
    óg
    -0.06
    atab
    -0.06
    iegel
    -0.06
    POSITIVE LOGITS
    fy
    0.07
     attached
    0.07
     Attached
    0.07
    иÑģлов
    0.06
    paren
    0.06
    oog
    0.06
    ÙĨز
    0.06
    .ai
    0.06
    Attached
    0.06
    spender
    0.06
    Activations Density 0.105%

    No Known Activations