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. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44247
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistical data

    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
    _GB
    -0.07
    ancell
    -0.06
    éĢģæĸĻçĦ¡æĸĻ
    -0.06
    ÂĢÂĻ
    -0.06
    ừng
    -0.06
    ;</
    -0.06
    -License
    -0.06
    ä¾¡æł¼
    -0.06
    .parseFloat
    -0.06
     Ấ
    -0.06
    POSITIVE LOGITS
     NA
    0.08
     
    0.08
     na
    0.08
     âĨĵ
    0.07
     n
    0.07
     Decre
    0.07
     view
    0.07
     decrease
    0.07
    _increase
    0.06
     Na
    0.06
    Activations Density 0.005%

    No Known Activations