© 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. 55745
    Prev
    Next
    INDEX
    Explanations

    technical terms and language related to programming and web development elements

    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
    utsch
    -0.09
    makt
    -0.08
    AIN
    -0.07
    енÑĤов
    -0.07
    kili
    -0.07
    uld
    -0.07
    icator
    -0.06
    ellant
    -0.06
    issance
    -0.06
    abel
    -0.06
    POSITIVE LOGITS
    es
    0.10
    ese
    0.08
    ns
    0.08
    Ñĭ
    0.07
    们
    0.07
    ën
    0.07
    ů
    0.07
    ům
    0.07
    nya
    0.07
    mes
    0.07
    Activations Density 0.075%

    No Known Activations