© 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. 130691
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and concepts related to graphs and inequalities

    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
    uxtap
    -0.07
    .documentation
    -0.07
    atak
    -0.07
    ูà¹Ī
    -0.07
    ặ
    -0.06
    ÑĢии
    -0.06
    ncy
    -0.06
    znik
    -0.06
    reon
    -0.06
    sembling
    -0.06
    POSITIVE LOGITS
     minus
    0.07
    argout
    0.07
    -wide
    0.06
    ale
    0.06
    amba
    0.06
    yo
    0.06
    569
    0.06
     Shoulder
    0.06
    imal
    0.06
    ieri
    0.06
    Activations Density 0.177%

    No Known Activations