© 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. 59529
    Prev
    Next
    INDEX
    Explanations

    terms related to real estate information and 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
    ема
    -0.08
    ög
    -0.07
    Ú©Ø´
    -0.06
    PrimaryKey
    -0.06
    ạ
    -0.06
    enu
    -0.06
    eci
    -0.06
    ovy
    -0.06
    ä¿¡
    -0.06
    INET
    -0.06
    POSITIVE LOGITS
     aside
    0.08
     Hell
    0.08
     hell
    0.08
    Hell
    0.07
    frey
    0.06
     strictly
    0.06
    hell
    0.06
    	Copyright
    0.06
     STRICT
    0.06
     Mey
    0.06
    Activations Density 0.012%

    No Known Activations