© 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. 9-LLAMASCOPE-RES-131K
    11. 97104
    Prev
    Next
    INDEX
    Explanations

    themes of hope, service, and community support for the marginalized

    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
    chter
    -0.07
     gaz
    -0.06
    irts
    -0.06
    mez
    -0.06
    iston
    -0.06
    ylon
    -0.06
    idis
    -0.06
    UDA
    -0.06
    cka
    -0.06
    mann
    -0.06
    POSITIVE LOGITS
    çĵľ
    0.07
     Huss
    0.07
    BindingUtil
    0.06
    .ascii
    0.06
     ÅĻÃŃ
    0.06
    oldur
    0.06
    essor
    0.06
    erville
    0.06
     Assurance
    0.06
    ÙĪست
    0.06
    Activations Density 0.005%

    No Known Activations