© 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. 27316
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases or expressions

    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
    appen
    -0.08
    vic
    -0.07
    uther
    -0.07
    oyal
    -0.06
    vice
    -0.06
    jev
    -0.06
    оÑĤÑĮ
    -0.06
    anca
    -0.06
    enci
    -0.06
    iant
    -0.06
    POSITIVE LOGITS
     are
    0.10
     ones
    0.09
     were
    0.07
     can
    0.07
     have
    0.07
    -fontawesome
    0.06
    779
    0.06
    ones
    0.06
     cannot
    0.06
    ané
    0.06
    Activations Density 0.027%

    No Known Activations