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. 5074
    Prev
    Next
    INDEX
    Explanations

    genre classifications and associated labels for media content

    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
    ades
    -0.07
    ůj
    -0.06
    moth
    -0.06
     Fus
    -0.06
     pain
    -0.06
    amus
    -0.06
    ден
    -0.06
    bourg
    -0.06
     ä¹
    -0.06
     Raised
    -0.06
    POSITIVE LOGITS
    êµ´
    0.07
    Ñıви
    0.07
    askan
    0.07
    acro
    0.07
     Fahr
    0.06
    allas
    0.06
    pdo
    0.06
    ÙħÙĦØ©
    0.06
    mir
    0.06
    سر
    0.06
    Activations Density 0.002%

    No Known Activations