© 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 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. 3686
    Prev
    Next
    INDEX
    Explanations

    numerical references or identifiers in documents

    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
    ellers
    -0.08
    orrent
    -0.07
    TN
    -0.07
    anou
    -0.07
    eller
    -0.07
    ética
    -0.07
    atical
    -0.07
    RIA
    -0.07
    aces
    -0.07
     inval
    -0.07
    POSITIVE LOGITS
    iot
    0.06
    lew
    0.06
    ikel
    0.06
    heim
    0.06
    æ´ŀ
    0.06
    ors
    0.06
    abela
    0.06
    (es
    0.06
     nád
    0.06
     poj
    0.06
    Activations Density 0.014%

    No Known Activations