© 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. 9-LLAMASCOPE-RES-131K
    11. 96286
    Prev
    Next
    INDEX
    Explanations

    amenities and features of accommodations

    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
    ensus
    -0.06
    oring
    -0.06
    quer
    -0.06
    awi
    -0.06
    kaar
    -0.06
     Ped
    -0.05
    ution
    -0.05
    arde
    -0.05
     specifically
    -0.05
    yard
    -0.05
    POSITIVE LOGITS
    -equiv
    0.07
     pornos
    0.07
    /*------------------------------------------------
    0.07
     воÑĤ
    0.07
    pdata
    0.07
    ehr
    0.07
    _EXPI
    0.07
    .Serialization
    0.07
    üb
    0.06
    -HT
    0.06
    Activations Density 0.015%

    No Known Activations