© 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. 74632
    Prev
    Next
    INDEX
    Explanations

    copyright symbols and their variations

    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
    ̣
    -0.08
    oro
    -0.07
    оÑĢаз
    -0.06
    Tween
    -0.06
    prec
    -0.06
    FAULT
    -0.06
    obot
    -0.06
    Ｌ
    -0.06
    631
    -0.06
    ılıç
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.08
    ;amp
    0.07
    unca
    0.06
    .spi
    0.06
    ativa
    0.06
     Ry
    0.06
     Budget
    0.05
     Sawyer
    0.05
     rasp
    0.05
    (OpCodes
    0.05
    Activations Density 0.003%

    No Known Activations