© 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. 85677
    Prev
    Next
    INDEX
    Explanations

    symbols or special characters used to denote lists or categories

    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
    jÃŃt
    -0.06
    oop
    -0.06
    awan
    -0.06
    aces
    -0.06
    ermal
    -0.06
    avax
    -0.06
    ocl
    -0.06
    дн
    -0.06
     Composer
    -0.06
    dbus
    -0.06
    POSITIVE LOGITS
    essen
    0.07
    gay
    0.07
    ï¸ı
    0.07
    ovic
    0.07
    agma
    0.06
    chez
    0.06
    eto
    0.06
    niest
    0.06
    osu
    0.06
    ertino
    0.06
    Activations Density 0.007%

    No Known Activations