© 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. 57293
    Prev
    Next
    INDEX
    Explanations

    quotes and phrases that indicate opinions or perspectives

    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
    amt
    -0.07
    _pemb
    -0.06
    abant
    -0.06
     me
    -0.06
    allis
    -0.06
     reportedly
    -0.06
     meis
    -0.06
    bum
    -0.06
    479
    -0.06
    iband
    -0.06
    POSITIVE LOGITS
    Calibri
    0.07
    êu
    0.06
     there
    0.06
    aton
    0.06
    zyst
    0.06
    uzz
    0.06
    enson
    0.06
    ela
    0.06
    />.↵↵
    0.06
     whenever
    0.06
    Activations Density 0.061%

    No Known Activations