© 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. 56125
    Prev
    Next
    INDEX
    Explanations

    collective statements or actions related to community engagement or identity

    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
     ins
    -0.06
    اÙĪر
    -0.06
    istant
    -0.06
     Mont
    -0.06
    ermann
    -0.06
     Cal
    -0.05
    esc
    -0.05
     Ins
    -0.05
     Old
    -0.05
    ammad
    -0.05
    POSITIVE LOGITS
    بÙĪاسطة
    0.07
    -scrollbar
    0.07
    _RUNTIME
    0.07
    aille
    0.07
    _NC
    0.06
    agina
    0.06
    Intialized
    0.06
    _Parms
    0.06
     createState
    0.06
    igin
    0.06
    Activations Density 0.002%

    No Known Activations