© 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. 95320
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical data or statistics

    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
     Icelandic
    -0.06
     Noel
    -0.06
     ÄĮech
    -0.06
    оже
    -0.06
    alf
    -0.06
    alm
    -0.06
    Northern
    -0.05
     Yankee
    -0.05
    üz
    -0.05
    /Documents
    -0.05
    POSITIVE LOGITS
     London
    0.09
     New
    0.08
     пеÑĢеп
    0.07
    London
    0.07
    lÃŃÄį
    0.07
    egasus
    0.07
    ünchen
    0.07
    orestation
    0.07
    chemas
    0.07
    esktop
    0.07
    Activations Density 0.021%

    No Known Activations