© 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. 61516
    Prev
    Next
    INDEX
    Explanations

    references to inventory and administrative functions in a system

    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
    htags
    -0.07
    stype
    -0.06
    емон
    -0.06
    /*č↵
    -0.06
    orough
    -0.06
    ault
    -0.05
    ephy
    -0.05
    -helper
    -0.05
    piry
    -0.05
    hotmail
    -0.05
    POSITIVE LOGITS
    :///
    0.09
    /her
    0.08
    ://
    0.07
    jn
    0.07
     же
    0.07
    UTERS
    0.07
    usch
    0.07
    /the
    0.07
    ertino
    0.07
    hq
    0.06
    Activations Density 0.038%

    No Known Activations