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. 72607
    Prev
    Next
    INDEX
    Explanations

    mentions of technology and services related to media and entertainment

    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
    ibel
    -0.07
    اÙĬÙĦ
    -0.07
    ulen
    -0.07
    ëŁ
    -0.07
    rylic
    -0.07
    gary
    -0.06
    PTH
    -0.06
    steen
    -0.06
    iegel
    -0.06
    gx
    -0.06
    POSITIVE LOGITS
    ONGL
    0.07
    istica
    0.06
    à¥įतन
    0.06
    ichert
    0.06
    641
    0.06
    ocache
    0.06
    chai
    0.06
    Clause
    0.06
     kenn
    0.06
    ù
    0.06
    Activations Density 0.004%

    No Known Activations