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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 88425
    Prev
    Next
    INDEX
    Explanations

    themes of love and obligation towards neighbors and community

    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
    ÑĤÑı
    -0.07
    bolt
    -0.07
    umb
    -0.06
    andal
    -0.06
    زد
    -0.06
    alo
    -0.06
    ayd
    -0.06
    rides
    -0.06
    mium
    -0.06
    ogan
    -0.06
    POSITIVE LOGITS
     fellow
    0.18
     Fellow
    0.13
     neighbor
    0.12
     neighbour
    0.11
     neighbors
    0.10
     human
    0.10
     neighbours
    0.09
    neighbors
    0.09
    human
    0.08
    _neighbor
    0.08
    Activations Density 0.054%

    No Known Activations