© 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. 60431
    Prev
    Next
    INDEX
    Explanations

    occurrences of geographical locations and related numerical data

    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
    è¾ŀ
    -0.08
    inea
    -0.07
    ombo
    -0.07
    ãģªãģĮ
    -0.07
    olean
    -0.07
     anzeigen
    -0.07
    baÅŁ
    -0.07
    å±¥
    -0.07
    indx
    -0.06
    lene
    -0.06
    POSITIVE LOGITS
    eld
    0.09
     held
    0.08
     hosted
    0.07
     Marriott
    0.07
    verb
    0.06
    elden
    0.06
     Rust
    0.06
     registration
    0.06
    ÙĦا
    0.06
    ysi
    0.06
    Activations Density 0.024%

    No Known Activations