© 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. 15-LLAMASCOPE-RES-131K
    11. 26699
    Prev
    Next
    INDEX
    Explanations

    instances of formal documentation and analysis in legal contexts

    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
    iasi
    -0.08
    .sessions
    -0.07
    iran
    -0.07
     ÑģпÑĢи
    -0.07
     ÑĤипа
    -0.07
    okud
    -0.07
    :border
    -0.07
    inka
    -0.07
    preload
    -0.07
    ulen
    -0.07
    POSITIVE LOGITS
     arguments
    0.07
    oren
    0.06
    Arguments
    0.06
     factors
    0.06
    aoke
    0.06
     carefully
    0.06
     inputs
    0.06
     evidence
    0.06
     available
    0.06
     provided
    0.06
    Activations Density 0.012%

    No Known Activations