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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26769
    Prev
    Next
    INDEX
    Explanations

    references to authorities and organizations involved in health and community services

    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
    çīĩ
    -0.07
    Ø´ÙĨ
    -0.06
     illum
    -0.06
     erf
    -0.06
    arda
    -0.06
    unya
    -0.06
    _activ
    -0.06
    ıyı
    -0.06
    Chi
    -0.06
    agu
    -0.06
    POSITIVE LOGITS
    çĶ¨äºİ
    0.07
    anel
    0.07
     Ahead
    0.06
    enko
    0.06
    INCT
    0.06
     Pil
    0.06
    stdcall
    0.06
    iến
    0.06
    ©
    0.06
    aft
    0.06
    Activations Density 0.048%

    No Known Activations