© 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. 39852
    Prev
    Next
    INDEX
    Explanations

    product information, specifically related to laptops and their components

    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
    itos
    -0.07
    iro
    -0.07
    ito
    -0.07
    iral
    -0.07
    iyi
    -0.06
     Hearts
    -0.06
    RTOS
    -0.06
    ivre
    -0.06
     جÙħ
    -0.06
    otify
    -0.06
    POSITIVE LOGITS
     soup
    0.08
     replacements
    0.07
    attery
    0.07
     replacement
    0.07
    tery
    0.07
    adele
    0.07
    battery
    0.07
    soup
    0.07
    replacement
    0.07
     supper
    0.07
    Activations Density 0.001%

    No Known Activations