© 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. 17-LLAMASCOPE-RES-131K
    11. 74047
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical maintenance or issues

    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
     noh
    -0.07
    _ARGUMENT
    -0.07
    gaard
    -0.07
    .wp
    -0.06
     रहत
    -0.06
    xac
    -0.06
    ohen
    -0.06
    "go
    -0.06
    íĥĢ
    -0.06
    '=>['
    -0.06
    POSITIVE LOGITS
     probably
    0.11
     somewhere
    0.10
    probably
    0.09
     Probably
    0.09
     either
    0.09
    Probably
    0.08
     perhaps
    0.08
    either
    0.08
     possibly
    0.08
     Either
    0.08
    Activations Density 0.030%

    No Known Activations