© 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. 9-LLAMASCOPE-RES-131K
    11. 96978
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and class declarations

    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
    .DropDown
    -0.07
     Äįin
    -0.07
     fond
    -0.07
    "@
    -0.06
    abaj
    -0.06
    JR
    -0.06
    ski
    -0.06
    /topics
    -0.06
    adden
    -0.06
     ÄijÃłi
    -0.06
    POSITIVE LOGITS
    atr
    0.06
    ymous
    0.06
     resizable
    0.06
    uka
    0.06
    ola
    0.06
    anie
    0.06
    odable
    0.06
    ìĭľìĺ¤
    0.06
    lient
    0.06
    ermal
    0.06
    Activations Density 0.000%

    No Known Activations