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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118653
    Prev
    Next
    INDEX
    Explanations

    words associated with geographic locations or settings

    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
    zel
    -0.09
    onga
    -0.08
    udu
    -0.07
    hea
    -0.07
     ><?
    -0.07
    èĻŁ
    -0.07
    htar
    -0.07
    /effects
    -0.07
    moz
    -0.07
    engu
    -0.07
    POSITIVE LOGITS
    ities
    0.06
     Trojan
    0.06
     Higgins
    0.06
    mente
    0.06
    âĢĮترÛĮÙĨ
    0.06
    ë¡ł
    0.05
    idad
    0.05
    itty
    0.05
    æĻ¯
    0.05
     suf
    0.05
    Activations Density 0.001%

    No Known Activations