© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 2873
    Prev
    Next
    INDEX
    Explanations

    names of individuals and organizations involved in leadership roles or actions

    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
    .timeScale
    -0.06
    eres
    -0.06
     anew
    -0.06
    麦
    -0.06
    edef
    -0.06
     Allied
    -0.06
    undi
    -0.06
     sıras
    -0.06
    .Localization
    -0.06
    .yy
    -0.06
    POSITIVE LOGITS
     also
    0.08
     similarly
    0.08
    also
    0.08
     ebenfalls
    0.08
     également
    0.08
    ä¹Łæľī
    0.07
     intervene
    0.07
     intervened
    0.07
    åīĩ
    0.07
     ÑĤоже
    0.07
    Activations Density 0.107%

    No Known Activations