© 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. 124116
    Prev
    Next
    INDEX
    Explanations

    references to programs or plans aimed at community support and improvement

    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
    leigh
    -0.07
    unga
    -0.07
    rint
    -0.07
    ulk
    -0.07
    jin
    -0.07
    èĬ
    -0.06
    ä¹Ī
    -0.06
     ÅŁek
    -0.06
    cola
    -0.06
     colum
    -0.06
    POSITIVE LOGITS
    -program
    0.09
     programs
    0.08
     program
    0.08
     Programs
    0.08
     programas
    0.08
     programmes
    0.08
    Program
    0.08
     пÑĢогÑĢам
    0.08
     Program
    0.08
    programs
    0.07
    Activations Density 0.024%

    No Known Activations