© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71920
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of buildings and structures

    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
    ÑģоÑĤ
    -0.08
    metros
    -0.07
    SED
    -0.07
    (æ°´
    -0.07
    zimmer
    -0.07
    ẳng
    -0.06
    ¦y
    -0.06
    bih
    -0.06
    ahoo
    -0.06
    SHIP
    -0.06
    POSITIVE LOGITS
     storage
    0.07
    azz
    0.06
    ag
    0.06
    -storage
    0.06
     Goldberg
    0.06
    uke
    0.06
     inse
    0.06
    oden
    0.06
     Jonas
    0.06
    refix
    0.06
    Activations Density 0.011%

    No Known Activations