© 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. 96273
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and symbols

    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
     RECEIVER
    -0.08
    /commons
    -0.07
    sov
    -0.07
    quat
    -0.07
    aji
    -0.07
    etsk
    -0.07
    ifo
    -0.07
    ulg
    -0.07
    otos
    -0.07
    öm
    -0.07
    POSITIVE LOGITS
     доÑĢ
    0.06
    733
    0.06
     perv
    0.06
    ReuseIdentifier
    0.05
    823
    0.05
    ниÑĤ
    0.05
    ัà¸įà¸į
    0.05
     Fut
    0.05
    à¥ĥ
    0.05
    >Hello
    0.05
    Activations Density 0.015%

    No Known Activations