© 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 EvalsExportsinterp-engineNEWAPI 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. 97845
    Prev
    Next
    INDEX
    Explanations

    key terms related to complex mathematics or theoretical constructs

    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
    atsu
    -0.07
    олоÑĤ
    -0.07
    meli
    -0.07
    nun
    -0.07
    оби
    -0.07
     Nations
    -0.06
    pok
    -0.06
    piler
    -0.06
    åĨł
    -0.06
    ké
    -0.06
    POSITIVE LOGITS
    ogui
    0.07
     Affero
    0.06
    td
    0.06
    pta
    0.06
    æ¢ģ
    0.06
    arius
    0.06
    istrov
    0.06
     Nom
    0.06
    Campo
    0.06
    zas
    0.06
    Activations Density 0.000%

    No Known Activations