© 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. 128806
    Prev
    Next
    INDEX
    Explanations

    logical operators and terms associated with programming or computing

    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
     dam
    -0.07
     caps
    -0.07
    Caps
    -0.06
     et
    -0.06
    aus
    -0.06
    least
    -0.05
     united
    -0.05
    ä¸Ģ人
    -0.05
    ins
    -0.05
    aras
    -0.05
    POSITIVE LOGITS
     newer
    0.09
    <?↵
    0.07
     pozdÄĽ
    0.07
    engo
    0.07
     older
    0.07
     latest
    0.07
    .Guna
    0.07
    groupBox
    0.07
    alien
    0.07
     younger
    0.07
    Activations Density 0.005%

    No Known Activations