© 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 EvalsExportsinterp-engineNEWAPI 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. 72501
    Prev
    Next
    INDEX
    Explanations

    items related to earrings and ear accessories

    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
    bound
    -0.08
    rott
    -0.07
    ieg
    -0.07
    GuidId
    -0.07
    anga
    -0.07
    zug
    -0.06
     spine
    -0.06
    çĽĸ
    -0.06
    /sdk
    -0.06
    iffs
    -0.06
    POSITIVE LOGITS
    avax
    0.07
    물
    0.07
    Ïģή
    0.06
     PIO
    0.06
     kho
    0.06
     earrings
    0.06
    FAQ
    0.06
     stainless
    0.06
    /devices
    0.06
     slack
    0.06
    Activations Density 0.001%

    No Known Activations