© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4005
    Prev
    Next
    INDEX
    Explanations

    offers related to free services or promotions

    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
    Commerce
    -0.07
    æ¢ģ
    -0.07
    kontakte
    -0.07
    apper
    -0.06
    ptic
    -0.06
    аÑĢод
    -0.06
    _CELL
    -0.06
    ength
    -0.06
    sonian
    -0.06
    ogle
    -0.06
    POSITIVE LOGITS
     fleet
    0.07
     Hass
    0.06
     Wit
    0.06
    é»
    0.06
    åĩĿ
    0.06
     Fleet
    0.06
    Bid
    0.06
    hausen
    0.06
    alytics
    0.06
     Peng
    0.06
    Activations Density 0.001%

    No Known Activations