© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 75397
    Prev
    Next
    INDEX
    Explanations

    snippets of code, particularly in Python, related to HTML or XML element creation

    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
    rades
    -0.07
    uitka
    -0.07
     âĹĦ
    -0.07
    746
    -0.07
    横
    -0.07
    еÑģа
    -0.07
    abbit
    -0.06
    ĺìĿ´
    -0.06
    semb
    -0.06
    _SI
    -0.06
    POSITIVE LOGITS
     div
    0.07
     Div
    0.07
     soup
    0.07
    èī
    0.07
     em
    0.06
     Kurd
    0.06
     Fernando
    0.06
    oup
    0.06
     Soup
    0.06
    ulse
    0.06
    Activations Density 0.004%

    No Known Activations