© 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. 9-LLAMASCOPE-RES-131K
    11. 97392
    Prev
    Next
    INDEX
    Explanations

    numerical values in a technical context, likely related to error messages or debugging information

    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
    ngrx
    -0.07
    SelectionMode
    -0.06
    ÙĨد
    -0.06
    лом
    -0.06
    oup
    -0.06
    ãĥĥãĥĦ
    -0.06
    PullParser
    -0.06
    ostel
    -0.06
    gnu
    -0.06
    \Bridge
    -0.06
    POSITIVE LOGITS
    _builtin
    0.07
    ialis
    0.07
     Hague
    0.07
    ilan
    0.06
    ób
    0.06
    bat
    0.06
    evin
    0.06
    ìĤ´
    0.06
    ning
    0.06
    íĸī
    0.06
    Activations Density 0.004%

    No Known Activations