© 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. 17-LLAMASCOPE-RES-131K
    11. 4000
    Prev
    Next
    INDEX
    Explanations

    locations and places related to creative or professional activities

    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
    ampie
    -0.08
    ÑĪи
    -0.07
    stal
    -0.07
    виÑĤ
    -0.07
    ủy
    -0.07
     ÄijÃŃch
    -0.07
    اط
    -0.06
    agar
    -0.06
    benh
    -0.06
    cio
    -0.06
    POSITIVE LOGITS
     located
    0.07
    ISA
    0.07
     suburb
    0.06
    isclosed
    0.06
     Silver
    0.06
    ardy
    0.06
    UED
    0.06
    located
    0.06
    URAL
    0.06
    mma
    0.06
    Activations Density 0.025%

    No Known Activations