© 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. 87695
    Prev
    Next
    INDEX
    Explanations

    possessive forms and contractions indicating ownership or association

    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
    .scalablytyped
    -0.07
    _PKG
    -0.07
    [Math
    -0.07
    _COMPILE
    -0.06
    ema
    -0.06
    iid
    -0.06
    cepts
    -0.06
    ãĥ¼ãĥ
    -0.06
    enga
    -0.06
    大åħ¨
    -0.06
    POSITIVE LOGITS
     version
    0.08
    åŃĿ
    0.07
    exion
    0.07
     system
    0.07
    /n
    0.06
    ccak
    0.06
    /Main
    0.06
    WO
    0.06
    996
    0.06
    ámara
    0.06
    Activations Density 0.020%

    No Known Activations