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

    Neuronpedia

    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. 75945
    Prev
    Next
    INDEX
    Explanations

    geographical references to California, specifically related to educational institutions

    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
    orem
    -0.07
    apt
    -0.07
    thy
    -0.06
    ilion
    -0.06
    glas
    -0.06
    dden
    -0.06
    513
    -0.06
    uard
    -0.06
    lient
    -0.05
    velt
    -0.05
    POSITIVE LOGITS
    ÙĨس
    0.09
    (EC
    0.08
     SavaÅŁ
    0.08
    unun
    0.07
    наÑĢÑĥж
    0.07
    FetchRequest
    0.07
    setState
    0.07
    ifornia
    0.07
    _Property
    0.07
     dobr
    0.07
    Activations Density 0.007%

    No Known Activations