© 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. 4093
    Prev
    Next
    INDEX
    Explanations

    elements related to technical specifications or structured data formats

    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
    ngle
    -0.06
    igel
    -0.06
    akat
    -0.06
    ifr
    -0.06
     Shade
    -0.06
    afort
    -0.06
    rott
    -0.06
    ab
    -0.06
    ç½
    -0.06
    _requires
    -0.05
    POSITIVE LOGITS
    laden
    0.07
    .Generated
    0.07
    ascus
    0.07
    alker
    0.07
    串
    0.07
     -*-č↵
    0.07
     xsi
    0.07
    imals
    0.07
    ç£
    0.06
    ÙĪراÙĨ
    0.06
    Activations Density 0.000%

    No Known Activations