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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106117
    Prev
    Next
    INDEX
    Explanations

    terms related to self-service functions and support efficiency

    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
    ëį°ìĿ´íĬ¸
    -0.08
    .getAs
    -0.07
    alen
    -0.07
     acomp
    -0.07
    aland
    -0.06
     opat
    -0.06
     Inspir
    -0.06
    ched
    -0.06
    ÑĢÑĥÑģ
    -0.06
    818
    -0.06
    POSITIVE LOGITS
     admin
    0.10
     Admin
    0.10
    Admin
    0.09
     administrator
    0.09
     admins
    0.08
     ADMIN
    0.08
    _admin
    0.08
    ê´Ģ리ìŀIJ
    0.08
    admin
    0.08
    管çIJĨåijĺ
    0.08
    Activations Density 0.021%

    No Known Activations