© 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. 17-LLAMASCOPE-RES-131K
    11. 73924
    Prev
    Next
    INDEX
    Explanations

    structured elements and their relationships in a system

    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
    jal
    -0.06
    kili
    -0.06
    hoff
    -0.06
     ÑĤÑĥ
    -0.06
    åª
    -0.06
    .AI
    -0.06
    enso
    -0.06
    iga
    -0.06
    ãĤ·ãĥªãĥ¼ãĤº
    -0.06
     deton
    -0.06
    POSITIVE LOGITS
    .metamodel
    0.06
    OfClass
    0.06
    ÑĨо
    0.06
     Pickup
    0.06
     Samp
    0.06
    abouts
    0.06
    æ¬
    0.06
     Bug
    0.06
     diagrams
    0.06
     Pet
    0.06
    Activations Density 0.005%

    No Known Activations