© 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. 9-LLAMASCOPE-RES-131K
    11. 96254
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to digital signal processing

    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
    athi
    -0.07
    borough
    -0.07
    Å¡ku
    -0.06
    SION
    -0.06
    obot
    -0.06
    isphere
    -0.06
    hed
    -0.06
    ores
    -0.06
    /dd
    -0.06
    uron
    -0.06
    POSITIVE LOGITS
    inand
    0.07
    tout
    0.07
     Wool
    0.06
     Ballard
    0.06
     Hammer
    0.06
    ">//
    0.06
     tout
    0.06
     Patch
    0.06
    uo
    0.06
     patch
    0.06
    Activations Density 0.097%

    No Known Activations