© 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. 9-LLAMASCOPE-RES-131K
    11. 95881
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographic locations and movement

    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
     Sense
    -0.08
     sense
    -0.07
    iz
    -0.06
    _SCREEN
    -0.06
     Fate
    -0.06
     Mir
    -0.06
    ania
    -0.06
     Mand
    -0.06
     Ð¡ÐŁ
    -0.05
    ly
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĥģ
    0.07
    訪
    0.07
    -validate
    0.07
    -toggler
    0.07
    etes
    0.06
    .FontStyle
    0.06
    غاÙĦ
    0.06
    pill
    0.06
    CEE
    0.06
     báo
    0.06
    Activations Density 0.013%

    No Known Activations