© 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. 93116
    Prev
    Next
    INDEX
    Explanations

    terms related to online environments and user interactions

    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
     dvd
    -0.07
    æĿ¡
    -0.07
    kees
    -0.07
     Boutique
    -0.06
    opo
    -0.06
    jeme
    -0.06
    nist
    -0.06
    ÙĨب
    -0.06
    ево
    -0.06
    pone
    -0.06
    POSITIVE LOGITS
     virtual
    0.10
    irtual
    0.08
     Virtual
    0.08
    virtual
    0.08
     space
    0.07
    ToWorld
    0.07
     xr
    0.07
     VR
    0.07
     world
    0.07
    Virtual
    0.07
    Activations Density 0.003%

    No Known Activations