© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 118016
    Prev
    Next
    INDEX
    Explanations

    terms related to constraints and their relationships within a mathematical or computational context

    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
     meisjes
    -0.08
    大åħ¨
    -0.07
    -src
    -0.07
    यन
    -0.07
    ãģ¨ãģĨ
    -0.07
    å®Įæķ´
    -0.07
    campo
    -0.07
    _upgrade
    -0.06
    uler
    -0.06
    ulative
    -0.06
    POSITIVE LOGITS
     near
    0.07
     unlikely
    0.07
     large
    0.06
     majority
    0.06
    near
    0.06
     small
    0.06
     especially
    0.06
    /small
    0.06
     values
    0.06
    ald
    0.05
    Activations Density 0.096%

    No Known Activations