© 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. 93219
    Prev
    Next
    INDEX
    Explanations

    details related to local historical sites and their geographical context

    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
    á»Ĩ
    -0.06
    hend
    -0.06
    âĶIJ
    -0.06
    bjerg
    -0.06
    èĪ
    -0.06
    ozor
    -0.06
    âĶ´
    -0.06
    æĸĩåѦ
    -0.06
    continental
    -0.06
    ellen
    -0.06
    POSITIVE LOGITS
     area
    0.26
    area
    0.21
     region
    0.19
     área
    0.18
     AREA
    0.18
     areas
    0.18
     Area
    0.18
    -area
    0.18
     vicinity
    0.17
    Area
    0.17
    Activations Density 0.156%

    No Known Activations