© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 119902
    Prev
    Next
    INDEX
    Explanations

    punctuation and numeric symbols

    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
    emmel
    -0.08
    èn
    -0.06
    zhou
    -0.06
    egie
    -0.06
    ÅĽli
    -0.06
    quist
    -0.06
     Poland
    -0.06
    ropp
    -0.06
    amac
    -0.06
    ôm
    -0.06
    POSITIVE LOGITS
    âĦĸâĦĸ
    0.07
    unal
    0.06
    تÙī
    0.06
    inium
    0.06
    ãĥªãĥ¼ãĤº
    0.06
    ekil
    0.06
    onica
    0.06
     Maya
    0.06
    еÑĢо
    0.06
     issu
    0.06
    Activations Density 0.019%

    No Known Activations