© 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. 106146
    Prev
    Next
    INDEX
    Explanations

    references to ownership or possession related to a website or service

    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
    oto
    -0.06
    .Runtime
    -0.06
     Carl
    -0.06
    agar
    -0.06
    atitis
    -0.06
    eyin
    -0.05
    chas
    -0.05
    esium
    -0.05
    :CGRect
    -0.05
    quil
    -0.05
    POSITIVE LOGITS
     website
    0.08
    FTA
    0.07
    elp
    0.07
    mart
    0.07
    website
    0.07
    itar
    0.07
    eni
    0.07
    xm
    0.06
    以æĿ¥
    0.06
    öh
    0.06
    Activations Density 0.001%

    No Known Activations