© 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 EvalsExportsAPI 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. 16453
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, particularly properties in code

    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
    etak
    -0.06
     unlink
    -0.06
    assi
    -0.06
    maxlength
    -0.06
    resse
    -0.06
    yne
    -0.06
     Enterprises
    -0.06
    à¥įà¤ľ
    -0.06
    çu
    -0.06
     crust
    -0.06
    POSITIVE LOGITS
    0.07
    hausen
    0.07
    <message
    0.07
    otos
    0.07
    aterangepicker
    0.07
    .AutoScaleMode
    0.06
    ohl
    0.06
    751
    0.06
     Estr
    0.06
    ition
    0.06
    Activations Density 0.000%

    No Known Activations