© 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. 130147
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and attributes

    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
    lines
    -0.07
    ore
    -0.07
     lines
    -0.06
    -lines
    -0.06
    ãģ¾ãģŁ
    -0.06
    -ed
    -0.06
    led
    -0.06
    _PK
    -0.06
    axon
    -0.06
     Rowe
    -0.06
    POSITIVE LOGITS
    icas
    0.07
     getopt
    0.07
    udev
    0.06
    erdem
    0.06
    azers
    0.06
    .Listener
    0.06
    ibase
    0.06
    åı¸
    0.06
    lü
    0.06
    èªĮ
    0.06
    Activations Density 0.002%

    No Known Activations