© 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. 3604
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and scientific data

    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
    hurst
    -0.06
    YLE
    -0.06
    ele
    -0.06
    ensis
    -0.06
    ROID
    -0.06
    ä¸īå¹´
    -0.06
     activeClassName
    -0.06
    æģ
    -0.06
    gap
    -0.06
    auer
    -0.06
    POSITIVE LOGITS
     units
    0.10
     unit
    0.10
    unit
    0.08
     Unit
    0.07
    _unit
    0.07
    units
    0.07
    åįķä½į
    0.07
     cent
    0.07
    .unit
    0.07
    Unit
    0.07
    Activations Density 0.114%

    No Known Activations