© 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. 128912
    Prev
    Next
    INDEX
    Explanations

    real estate features and descriptions related to property listings

    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
    AccountId
    -0.07
    ÆĴ
    -0.07
    opak
    -0.06
    oku
    -0.06
    _SOCKET
    -0.06
    stagram
    -0.06
    ighth
    -0.06
     Fle
    -0.06
    unic
    -0.06
    holm
    -0.06
    POSITIVE LOGITS
    elor
    0.08
     wcs
    0.07
    ela
    0.06
    elas
    0.06
    _SPELL
    0.06
    æľĽ
    0.06
    WC
    0.06
    ÄŁine
    0.06
    aze
    0.06
    nore
    0.06
    Activations Density 0.032%

    No Known Activations