© 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. 29228
    Prev
    Next
    INDEX
    Explanations

    HTML or XML syntax elements in the text

    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
    enty
    -0.06
    alis
    -0.06
    ateur
    -0.06
    ialis
    -0.06
    enko
    -0.06
    itoris
    -0.06
    epar
    -0.06
    ¿
    -0.06
    ator
    -0.06
    ango
    -0.06
    POSITIVE LOGITS
    Showing
    0.07
    charg
    0.07
     Imper
    0.07
    ichern
    0.06
    omatic
    0.06
    Mutable
    0.06
    deniz
    0.06
    XMLLoader
    0.06
     Showing
    0.06
     jumps
    0.06
    Activations Density 0.001%

    No Known Activations