© 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. 125583
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity or group, particularly in a supportive context

    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
    ette
    -0.06
    ws
    -0.06
    bs
    -0.06
     Mum
    -0.06
    .Cryptography
    -0.06
    mb
    -0.06
    å¥ı
    -0.06
     pres
    -0.06
    лин
    -0.05
    [
    -0.05
    POSITIVE LOGITS
    ifr
    0.09
    izzo
    0.08
    pNet
    0.08
     massaggi
    0.07
    emez
    0.07
    /*č↵
    0.07
    akan
    0.07
    embros
    0.07
    ê¸Ī
    0.07
     deser
    0.07
    Activations Density 0.013%

    No Known Activations