© 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. 125662
    Prev
    Next
    INDEX
    Explanations

    terms related to constraints in programming 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
    mun
    -0.08
    itate
    -0.07
    gie
    -0.07
    WF
    -0.07
    azı
    -0.06
    ifice
    -0.06
    аÑĢам
    -0.06
    splice
    -0.06
    cee
    -0.06
    ita
    -0.06
    POSITIVE LOGITS
    edly
    0.08
    ments
    0.07
    /conf
    0.07
    149
    0.07
    ment
    0.07
    ìĤ¬íķŃ
    0.07
    757
    0.06
    conds
    0.06
    ¼åIJĪ
    0.06
    uit
    0.06
    Activations Density 0.033%

    No Known Activations