© 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. 16523
    Prev
    Next
    INDEX
    Explanations

    numerical values representing significant statistics or measurements

    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
    gado
    -0.07
    dock
    -0.07
    CLUDING
    -0.07
    ilo
    -0.07
    .charset
    -0.06
    ter
    -0.06
    ated
    -0.06
    ton
    -0.06
    amin
    -0.06
    ental
    -0.06
    POSITIVE LOGITS
    ãİ
    0.06
    ingo
    0.06
    htar
    0.06
    @brief
    0.06
    inent
    0.06
    £¼
    0.06
    .scalajs
    0.06
    髪
    0.06
    unities
    0.06
    uez
    0.06
    Activations Density 0.007%

    No Known Activations