© 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. 38837
    Prev
    Next
    INDEX
    Explanations

    geographical locations and names related to bodies of water

    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
    inth
    -0.07
    avid
    -0.06
    ucci
    -0.06
     mastur
    -0.06
     sola
    -0.06
    iest
    -0.06
    rito
    -0.06
    جاÙĨ
    -0.06
    velle
    -0.06
    pped
    -0.06
    POSITIVE LOGITS
    ãģĵãĤĵãģ«
    0.07
    бÑĥдÑĮ
    0.07
    ̣
    0.07
    üst
    0.06
    acles
    0.06
    stial
    0.06
    ACLE
    0.06
     Whe
    0.06
    jsc
    0.06
     others
    0.06
    Activations Density 0.030%

    No Known Activations