© 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. 15-LLAMASCOPE-RES-131K
    11. 87750
    Prev
    Next
    INDEX
    Explanations

    programming-related errors or exceptions

    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
    stadt
    -0.06
    aris
    -0.06
    edis
    -0.05
     foreground
    -0.05
    unya
    -0.05
    -0.05
     Xavier
    -0.05
    iving
    -0.05
     Mills
    -0.05
    qu
    -0.05
    POSITIVE LOGITS
    Ư
    0.07
    .rawValue
    0.07
    ãĤ¤ãĥ³ãĥĪ
    0.07
    çī§
    0.07
    isateur
    0.07
    echa
    0.07
     åıĮ线
    0.07
    ViewState
    0.07
     침
    0.07
    rador
    0.07
    Activations Density 0.000%

    No Known Activations