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. 72554
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and numerical data in the text

    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
    amat
    -0.08
    .tc
    -0.07
    tings
    -0.07
    intl
    -0.07
    uraa
    -0.07
    ī
    -0.06
    HU
    -0.06
     putas
    -0.06
    _LOCAL
    -0.06
    unas
    -0.06
    POSITIVE LOGITS
    ãĤ·ãĤ¢
    0.07
    برد
    0.06
     Shin
    0.06
     Sherman
    0.06
    emon
    0.06
    StringRef
    0.06
     Elect
    0.06
     Bai
    0.06
    race
    0.06
    adows
    0.06
    Activations Density 0.001%

    No Known Activations