© 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. 95247
    Prev
    Next
    INDEX
    Explanations

    references to program instructions and their execution in a computing context

    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
     iso
    -0.06
    usat
    -0.06
    porate
    -0.06
     acrylic
    -0.06
    iso
    -0.06
    -property
    -0.06
    ieres
    -0.06
    eum
    -0.06
     HQ
    -0.06
    ÑĢаÑģÑĤа
    -0.06
    POSITIVE LOGITS
     programs
    0.08
     code
    0.08
    programs
    0.07
     Programs
    0.07
    hum
    0.07
     Blockly
    0.07
     instructions
    0.07
    human
    0.07
    PCODE
    0.07
     código
    0.07
    Activations Density 0.021%

    No Known Activations