© 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. 41245
    Prev
    Next
    INDEX
    Explanations

    possessive constructions, specifically instances of "is" followed by a noun indicating ownership

    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
    ÌĨ
    -0.08
    ig
    -0.07
    uto
    -0.07
    odos
    -0.07
    egin
    -0.06
    çĶŁçļĦ
    -0.06
    /The
    -0.06
    .Obj
    -0.06
    lah
    -0.06
     áº
    -0.06
    POSITIVE LOGITS
     themselves
    0.08
    /client
    0.07
     OWN
    0.07
    Enlarge
    0.06
    roller
    0.06
    ongyang
    0.06
     respective
    0.06
    ÏĥÏĥα
    0.06
    CCC
    0.06
    ãĥ¼ãĤ¸
    0.06
    Activations Density 0.033%

    No Known Activations