© 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. 40037
    Prev
    Next
    INDEX
    Explanations

    references to master bedrooms and suites in real estate descriptions

    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
    //{{
    -0.07
    ãĤĤãĤĬ
    -0.07
    PLIC
    -0.07
    aines
    -0.06
    alar
    -0.06
     acronym
    -0.06
     developmental
    -0.06
     Operation
    -0.06
     ç¨
    -0.06
    uin
    -0.06
    POSITIVE LOGITS
    uffle
    0.07
     suite
    0.06
    rena
    0.06
     Kir
    0.06
     double
    0.06
    -double
    0.06
     suites
    0.06
    -suite
    0.06
    ework
    0.06
    LER
    0.06
    Activations Density 0.006%

    No Known Activations