© 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 EvalsExportsinterp-engineNEWAPI 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. 74020
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate goals or actions involving movement towards something

    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
    anou
    -0.07
    anlar
    -0.07
    oco
    -0.06
    BackStack
    -0.06
    keley
    -0.06
    Memory
    -0.06
    cea
    -0.06
    urdu
    -0.06
    rawler
    -0.06
    iciel
    -0.06
    POSITIVE LOGITS
     grips
    0.08
    ãĤ¸ãĤ¢
    0.07
    iane
    0.07
    _via
    0.07
    tors
    0.07
     know
    0.06
    eri
    0.06
    км
    0.06
    ewe
    0.06
    tings
    0.06
    Activations Density 0.018%

    No Known Activations