© 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. 5-LLAMASCOPE-RES-131K
    11. 125725
    Prev
    Next
    INDEX
    Explanations

    references to glazes or sugary coatings in cooking

    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
    les
    -0.07
    ales
    -0.07
     éĩİ
    -0.07
     Geld
    -0.06
    isa
    -0.06
    еж
    -0.06
    cken
    -0.06
    ansa
    -0.06
    ãĥ¼ãĥĢ
    -0.06
    ãĤ¹ãĤ«
    -0.06
    POSITIVE LOGITS
    PROTO
    0.07
    prox
    0.07
    çħ§
    0.07
    /GL
    0.07
     pit
    0.07
    ĶåĽŀ
    0.07
    rics
    0.06
    ãĥ¼ãĥĨ
    0.06
    erna
    0.06
    _PRIORITY
    0.06
    Activations Density 0.001%

    No Known Activations