Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. MLP Out
    5. 29-LLAMASCOPE-MLP-131K
    6. 5062
    Prev
    Next
    INDEX
    Explanations

    specific financial or accounting terms and references

    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
    awy
    -0.07
    ãĥªãĤ«
    -0.07
    èŀ
    -0.06
    nemonic
    -0.06
    æ¤
    -0.06
    _ak
    -0.06
    ndern
    -0.06
     jan
    -0.06
     extractor
    -0.06
    ingles
    -0.06
    POSITIVE LOGITS
    eteria
    0.06
    eter
    0.06
    inker
    0.06
     intimid
    0.06
    arLayout
    0.06
    uel
    0.06
     Suarez
    0.06
    haven
    0.06
     Fl
    0.06
    uele
    0.06
    Activations Density 0.000%

    No Known Activations