© 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. 15-LLAMASCOPE-RES-131K
    11. 86870
    Prev
    Next
    INDEX
    Explanations

    keywords related to group participation and collaboration

    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
    ucker
    -0.08
    loo
    -0.07
    ick
    -0.07
     Trident
    -0.07
    afi
    -0.07
    ÐĴÐŀ
    -0.06
    jte
    -0.06
    eker
    -0.06
    код
    -0.06
    usz
    -0.06
    POSITIVE LOGITS
    /group
    0.12
    /team
    0.09
    /shared
    0.08
     halinde
    0.07
    /single
    0.07
    åħ±
    0.07
    share
    0.06
     aspect
    0.06
    /groups
    0.06
     dynamics
    0.06
    Activations Density 0.067%

    No Known Activations