© 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. 96488
    Prev
    Next
    INDEX
    Explanations

    references to conferences and publications related to engineering and technology

    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
    agan
    -0.07
    anine
    -0.07
    ä¹ĭä¸Ģ
    -0.06
    _USAGE
    -0.06
    annes
    -0.06
     Leigh
    -0.06
    íķĻ
    -0.06
    è¾
    -0.06
    irsch
    -0.06
     Weiner
    -0.06
    POSITIVE LOGITS
    Defaults
    0.07
    анÑģи
    0.07
    JsonValue
    0.07
    žel
    0.06
    antan
    0.06
    arie
    0.06
    uez
    0.06
    áºŃt
    0.06
    ekil
    0.06
     AVC
    0.06
    Activations Density 0.012%

    No Known Activations