© 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. 127510
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to licensing and permissions

    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
     Erotik
    -0.09
     xấu
    -0.08
    retim
    -0.08
    .SDK
    -0.08
    meli
    -0.08
    _ATTRIB
    -0.07
    дам
    -0.07
    ÙħÙĨد
    -0.07
    eria
    -0.07
    дÑı
    -0.07
    POSITIVE LOGITS
    437
    0.06
    ister
    0.06
    licer
    0.06
    ↵
    0.05
    727
    0.05
    gar
    0.05
    736
    0.05
     Control
    0.05
     offsetY
    0.05
    384
    0.05
    Activations Density 0.007%

    No Known Activations