© 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. 56624
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the absence of something or missing elements

    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
    анов
    -0.07
    PIO
    -0.07
     Thornton
    -0.07
    son
    -0.07
    uck
    -0.07
    erties
    -0.06
    toi
    -0.06
    .Registry
    -0.06
    POSITORY
    -0.06
    loi
    -0.06
    POSITIVE LOGITS
     altogether
    0.08
    issippi
    0.08
    pent
    0.07
     missing
    0.07
    missing
    0.07
    oten
    0.07
    pec
    0.07
    pell
    0.06
    poke
    0.06
    ess
    0.06
    Activations Density 0.008%

    No Known Activations