© 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. 77898
    Prev
    Next
    INDEX
    Explanations

    terms related to structural damage and deterioration

    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
    .Immutable
    -0.06
     Americas
    -0.06
     tÄĽ
    -0.06
     inaug
    -0.06
    ¶Į
    -0.06
    afia
    -0.06
     eskort
    -0.06
    equip
    -0.06
     ç¨
    -0.06
     upstream
    -0.05
    POSITIVE LOGITS
    esta
    0.08
    oba
    0.07
    ç´¯
    0.07
    emmel
    0.07
    pearance
    0.07
    ãĥ¡ãĥ©
    0.07
    á»Ļng
    0.06
    ODB
    0.06
    ç´Ķ
    0.06
    å¥Ī
    0.06
    Activations Density 0.004%

    No Known Activations