© 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. 29358
    Prev
    Next
    INDEX
    Explanations

    positive attributes and qualities related to films and storytelling

    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
    iot
    -0.07
    Ctx
    -0.07
    ervlet
    -0.07
    Ø·Ùĩ
    -0.06
    격
    -0.06
    oku
    -0.06
    ottom
    -0.06
    еди
    -0.06
    опаÑģ
    -0.06
    (æ°´
    -0.06
    POSITIVE LOGITS
     often
    0.09
    plots
    0.07
    ews
    0.07
     plots
    0.07
    Often
    0.07
    RLF
    0.07
    often
    0.07
     generally
    0.07
    ookies
    0.07
     Laden
    0.07
    Activations Density 0.011%

    No Known Activations