© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56972
    Prev
    Next
    INDEX
    Explanations

    phrases related to optimization problems and algorithms

    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
    ker
    -0.07
    pen
    -0.06
    igner
    -0.06
    ston
    -0.06
    que
    -0.06
     Jenner
    -0.06
    quia
    -0.06
    озв
    -0.06
    meno
    -0.06
    iston
    -0.06
    POSITIVE LOGITS
    ế
    0.09
    ervlet
    0.07
    Destructor
    0.07
    AXB
    0.07
    antwort
    0.07
    MimeType
    0.07
    NotSupportedException
    0.06
    nants
    0.06
    pollo
    0.06
    edia
    0.06
    Activations Density 0.046%

    No Known Activations