© 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. 72296
    Prev
    Next
    INDEX
    Explanations

    references to partnerships and collaborations in community events or initiatives

    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
    æ´
    -0.07
     huku
    -0.07
     isize
    -0.07
    uhl
    -0.07
    áo
    -0.07
    ť
    -0.07
     Ùħؤ
    -0.07
    GU
    -0.07
    /gui
    -0.07
    ço
    -0.07
    POSITIVE LOGITS
     local
    0.09
    iesel
    0.07
    local
    0.06
     locally
    0.06
    ouro
    0.06
     Werner
    0.06
     Rim
    0.06
    avir
    0.06
    ehr
    0.06
    uada
    0.06
    Activations Density 0.055%

    No Known Activations