© 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. 58771
    Prev
    Next
    INDEX
    Explanations

    the presence of the token "LG" in various contexts

    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
    umno
    -0.08
    ogne
    -0.07
    aire
    -0.07
    pond
    -0.06
    ulumi
    -0.06
    raph
    -0.06
    oice
    -0.06
    úsqueda
    -0.06
     DISCLAIM
    -0.06
     unh
    -0.06
    POSITIVE LOGITS
    eder
    0.08
    chop
    0.07
    edly
    0.07
    ï¸
    0.07
    Ì
    0.07
    ading
    0.07
    osomal
    0.07
    elik
    0.07
     latter
    0.07
    ÌĤ
    0.07
    Activations Density 0.023%

    No Known Activations