© 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. 39515
    Prev
    Next
    INDEX
    Explanations

    elements of code or programming constructs

    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
    á»ij
    -0.06
    ol
    -0.06
    Ñī
    -0.06
     Hick
    -0.06
    Ìģ
    -0.06
    ÑģÑĤи
    -0.06
    611
    -0.05
    ons
    -0.05
    Rs
    -0.05
    gage
    -0.05
    POSITIVE LOGITS
    inka
    0.08
    EIF
    0.08
    ãĤ¢ãĥ¼
    0.07
    addtogroup
    0.07
    AINS
    0.07
    _escape
    0.07
    _pins
    0.07
     tế
    0.07
    -webpack
    0.07
    .rad
    0.07
    Activations Density 0.004%

    No Known Activations