© 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. 17-LLAMASCOPE-RES-131K
    11. 56584
    Prev
    Next
    INDEX
    Explanations

    terms related to configuration and settings in a technical context

    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
    óż
    -0.07
    infeld
    -0.07
    amax
    -0.07
    еле
    -0.07
    etu
    -0.07
    azed
    -0.06
    erea
    -0.06
     Lin
    -0.06
     compared
    -0.06
    (#)
    -0.06
    POSITIVE LOGITS
     minus
    0.10
     плÑİ
    0.08
    minus
    0.07
     plus
    0.07
    _plus
    0.07
    vig
    0.06
     +
    0.06
    orianCalendar
    0.06
    _minus
    0.06
    .DEFAULT
    0.06
    Activations Density 0.080%

    No Known Activations