© 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. 126551
    Prev
    Next
    INDEX
    Explanations

    key elements related to the creative and technical aspects of filmmaking

    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
     spokes
    -0.07
    ****************************************************************************
    -0.07
    elor
    -0.07
    .googlecode
    -0.07
    //**↵
    -0.07
    jumbotron
    -0.06
    ToDevice
    -0.06
    _CPP
    -0.06
    aza
    -0.06
    âijł
    -0.06
    POSITIVE LOGITS
     initial
    0.06
    gom
    0.06
    ãĥ¼ãĥķ
    0.06
     growing
    0.06
     ones
    0.06
    dek
    0.06
     Noir
    0.06
     nef
    0.06
    larg
    0.06
    needed
    0.06
    Activations Density 0.000%

    No Known Activations