© 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. 15-LLAMASCOPE-RES-131K
    11. 524
    Prev
    Next
    INDEX
    Explanations

    references to appointments and roles within organizational structures

    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
    ãģĨãģ¡
    -0.07
    ĥĿ
    -0.07
     htons
    -0.07
    ì§ĵ
    -0.07
    ÑģÑĮ
    -0.07
    inux
    -0.07
    UserCode
    -0.07
    .nano
    -0.07
    REDIENT
    -0.07
    riter
    -0.07
    POSITIVE LOGITS
     instead
    0.07
    iah
    0.06
    instead
    0.06
    ihan
    0.06
     Concurrent
    0.06
     Burst
    0.06
     replace
    0.06
    iden
    0.06
     now
    0.06
    yy
    0.06
    Activations Density 0.006%

    No Known Activations