© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 125486
    Prev
    Next
    INDEX
    Explanations

    references to historical or architectural sites

    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
    ifter
    -0.08
    rollo
    -0.07
    ITE
    -0.07
    ffen
    -0.06
     thereof
    -0.06
    Rated
    -0.06
    asing
    -0.06
    ouses
    -0.06
    æķı
    -0.06
    eed
    -0.06
    POSITIVE LOGITS
     Canter
    0.06
    _tac
    0.06
    fails
    0.06
    acas
    0.06
     Blair
    0.06
     Chall
    0.06
    ças
    0.06
     Watt
    0.06
    piar
    0.06
     Salt
    0.06
    Activations Density 0.024%

    No Known Activations