© 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. 86117
    Prev
    Next
    INDEX
    Explanations

    code-related log management statements

    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
    emos
    -0.07
     voks
    -0.06
    æģĴ
    -0.06
     znam
    -0.06
    _FAULT
    -0.06
    è¡
    -0.06
    ucha
    -0.06
    .githubusercontent
    -0.06
    pla
    -0.06
     macht
    -0.06
    POSITIVE LOGITS
    eger
    0.08
    esda
    0.07
    dna
    0.07
    ÑĤим
    0.06
    hei
    0.06
    dz
    0.06
     Carry
    0.06
    icot
    0.06
     report
    0.06
    ubb
    0.06
    Activations Density 0.048%

    No Known Activations