© 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. 15-LLAMASCOPE-RES-131K
    11. 90137
    Prev
    Next
    INDEX
    Explanations

    elements related to uncertainties, measurements, and reports in various contexts

    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
    phere
    -0.08
    latlong
    -0.07
    uro
    -0.07
    ázev
    -0.07
    ë³µ
    -0.07
    æ´¥
    -0.07
    ÚĺÛĮ
    -0.07
    orex
    -0.07
    BOOLE
    -0.07
    /TT
    -0.07
    POSITIVE LOGITS
    quia
    0.06
    -wise
    0.06
    707
    0.06
     wise
    0.06
    ABI
    0.06
    dej
    0.06
    ASA
    0.06
     algun
    0.06
    352
    0.06
    bac
    0.06
    Activations Density 0.526%

    No Known Activations