© 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. 69492
    Prev
    Next
    INDEX
    Explanations

    references to licensing and legal terms

    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
    immel
    -0.07
    yers
    -0.06
    087
    -0.06
    isia
    -0.06
    glas
    -0.06
    ndon
    -0.06
    888
    -0.06
    87
    -0.06
    ENCH
    -0.06
    amo
    -0.06
    POSITIVE LOGITS
    ccione
    0.08
    ÙĤت
    0.07
    elize
    0.07
    okit
    0.07
    алÑĥ
    0.07
    etro
    0.07
    requirements
    0.07
    бÑĢа
    0.06
    SCAN
    0.06
    _Application
    0.06
    Activations Density 0.002%

    No Known Activations