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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 1201
    Prev
    Next
    INDEX
    Explanations

    phrases related to hosting and preparing for guests

    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
    rage
    -0.07
    rz
    -0.06
    ammed
    -0.06
     Guardian
    -0.06
    -online
    -0.06
    éĢ²
    -0.06
     Vital
    -0.06
    ras
    -0.06
     Rah
    -0.06
    it
    -0.06
    POSITIVE LOGITS
     guests
    0.10
     Guests
    0.09
     guest
    0.08
     Gä
    0.08
    Guest
    0.08
     гоÑģÑĤ
    0.07
     Guest
    0.07
     serving
    0.07
    ³
    0.07
    guest
    0.07
    Activations Density 0.010%

    No Known Activations