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

    Neuronpedia

    Jacobian LensNEW
    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. 84352
    Prev
    Next
    INDEX
    Explanations

    various types of electronic devices and their related accessories

    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
    lessly
    -0.07
    ä½
    -0.07
    /not
    -0.06
    ube
    -0.06
    人åĵ¡
    -0.06
    /original
    -0.06
    еÑģи
    -0.06
    tu
    -0.06
    åĬłå·¥
    -0.06
    ategorized
    -0.06
    POSITIVE LOGITS
    /table
    0.08
    械
    0.07
     series
    0.07
     models
    0.07
    /light
    0.07
     밾매
    0.06
    series
    0.06
    avana
    0.06
    usher
    0.06
    ew
    0.06
    Activations Density 0.039%

    No Known Activations