© 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. 79415
    Prev
    Next
    INDEX
    Explanations

    terms related to competition and constraints in various contexts

    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
    ico
    -0.06
     Fate
    -0.06
    ongyang
    -0.06
    ordan
    -0.06
    ój
    -0.06
     Gloss
    -0.06
    ujet
    -0.06
    _cv
    -0.06
     Sas
    -0.06
    /spec
    -0.06
    POSITIVE LOGITS
     nature
    0.10
     being
    0.10
    being
    0.08
     ëķĮ문
    0.08
    nature
    0.07
     proximity
    0.07
     considerations
    0.07
     Being
    0.07
     sendo
    0.07
     reasons
    0.07
    Activations Density 0.087%

    No Known Activations