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. 25-LLAMASCOPE-MLP-131K
    6. 72609
    Prev
    Next
    INDEX
    Explanations

    references to online content and social media

    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
     pre
    -0.06
    erm
    -0.06
    avo
    -0.06
    lsa
    -0.06
    enos
    -0.06
    IVO
    -0.06
    ë°
    -0.06
    268
    -0.06
    olle
    -0.06
    938
    -0.06
    POSITIVE LOGITS
    æĥħ
    0.07
    Compat
    0.07
    ÑĢÑĥп
    0.06
    æĻ¯
    0.06
    ypi
    0.06
    .STATUS
    0.06
    unar
    0.06
    æĹĭ
    0.06
    æģĭ
    0.06
    -LAST
    0.06
    Activations Density 0.004%

    No Known Activations