© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70769
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    lash
    -0.07
    uration
    -0.07
    Ñĵ
    -0.06
    _hal
    -0.06
    æĬ½
    -0.06
    SENS
    -0.06
    ONUS
    -0.06
    ÙĪØ³Øª
    -0.06
     [...]↵↵
    -0.06
    arias
    -0.06
    POSITIVE LOGITS
     ones
    0.09
    ãĤ¤ãĤº
    0.08
    iskey
    0.07
    aversable
    0.07
    oeff
    0.07
     Venez
    0.07
    isen
    0.06
    encer
    0.06
    ioni
    0.06
    idl
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.