© 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. 9-LLAMASCOPE-RES-131K
    11. 94990
    Prev
    Next
    INDEX
    Explanations

    references to waitstaff and their roles in dining or service settings

    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
    ÑĪÑĤ
    -0.07
    illez
    -0.06
    ikut
    -0.06
    eks
    -0.06
    stadt
    -0.06
     Viewing
    -0.06
     memcmp
    -0.06
     liken
    -0.06
    val
    -0.06
    iagnostics
    -0.06
    POSITIVE LOGITS
    MASTER
    0.07
    اÙĤØ©
    0.07
    andles
    0.06
    (Self
    0.06
    igidBody
    0.06
    _RESERVED
    0.06
    masters
    0.06
    åĿĽ
    0.06
    andal
    0.06
    Tip
    0.06
    Activations Density 0.004%

    No Known Activations