© 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 EvalsExportsinterp-engineNEWAPI 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. 5180
    Prev
    Next
    INDEX
    Explanations

    terms related to housing and real estate

    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
    iesta
    -0.08
    ubb
    -0.07
    resco
    -0.07
    chop
    -0.07
    ynth
    -0.06
    smouth
    -0.06
    chet
    -0.06
    è£ķ
    -0.06
    ying
    -0.06
     Mog
    -0.06
    POSITIVE LOGITS
    inden
    0.09
    keiten
    0.08
    uns
    0.07
    zell
    0.07
    ientos
    0.07
     åł
    0.07
    ros
    0.07
    anten
    0.06
    aves
    0.06
    us
    0.06
    Activations Density 0.002%

    No Known Activations