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. 72599
    Prev
    Next
    INDEX
    Explanations

    references to stories or storytelling

    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
    erli
    -0.07
    otton
    -0.07
    нод
    -0.07
    quences
    -0.07
    Neutral
    -0.07
    tesy
    -0.07
    анк
    -0.07
    нен
    -0.07
    è³¢
    -0.07
    omnia
    -0.07
    POSITIVE LOGITS
    elt
    0.06
     Cair
    0.06
    bug
    0.06
    asje
    0.06
    ar
    0.06
    /ar
    0.06
    oj
    0.06
     dy
    0.06
    byn
    0.05
    -sub
    0.05
    Activations Density 0.001%

    No Known Activations