© 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. 86248
    Prev
    Next
    INDEX
    Explanations

    details related to historical landmarks and memorials

    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
     nÃło
    -0.06
     inf
    -0.06
    664
    -0.06
     Ùħخت
    -0.06
     Orient
    -0.06
    ëģĶ
    -0.06
    438
    -0.06
    ,void
    -0.06
    æĹĹ
    -0.05
    orch
    -0.05
    POSITIVE LOGITS
     famous
    0.08
     iconic
    0.07
    lint
    0.07
     Washing
    0.07
     ünlü
    0.07
    hang
    0.07
    obel
    0.07
    ãĥªãĥ³
    0.07
     fert
    0.07
    kov
    0.06
    Activations Density 0.057%

    No Known Activations