© 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. 15-LLAMASCOPE-RES-131K
    11. 86470
    Prev
    Next
    INDEX
    Explanations

    references to epidemiological models and their implications

    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
    _PRINTF
    -0.07
     Busty
    -0.06
    097
    -0.06
    agers
    -0.06
    _inches
    -0.06
     Milf
    -0.06
    å·¡
    -0.06
    ALES
    -0.06
    eel
    -0.06
    仲
    -0.06
    POSITIVE LOGITS
    .fac
    0.07
     community
    0.06
    orse
    0.06
     Disease
    0.06
     later
    0.06
    yw
    0.06
    partment
    0.06
    igo
    0.06
     peak
    0.06
    peak
    0.06
    Activations Density 0.011%

    No Known Activations