© 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. 56797
    Prev
    Next
    INDEX
    Explanations

    geographical references and eligibility criteria related to locations

    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
    Ĥ¹
    -0.07
    ĵ¨
    -0.07
    isko
    -0.07
    efa
    -0.06
    igel
    -0.06
    aze
    -0.06
    ader
    -0.06
    ager
    -0.06
    éo
    -0.06
    ιά
    -0.06
    POSITIVE LOGITS
     involved
    0.07
    enen
    0.07
    715
    0.07
    eken
    0.07
     Cah
    0.07
    etting
    0.07
     representation
    0.06
     locations
    0.06
    pj
    0.06
     hosting
    0.06
    Activations Density 0.025%

    No Known Activations