© 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. 120302
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate characteristics or qualities of systems or entities

    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
    trinsic
    -0.09
    ysa
    -0.07
    inctions
    -0.07
    ection
    -0.07
    .STATUS
    -0.07
    chet
    -0.07
    oplevel
    -0.07
    setDefault
    -0.07
    /Area
    -0.07
    opup
    -0.07
    POSITIVE LOGITS
     lack
    0.07
     absence
    0.07
     increased
    0.06
     high
    0.06
     low
    0.06
     Ø£ÙĨÙĩا
    0.06
    IDA
    0.06
     Mercy
    0.06
     Kop
    0.06
    :↵
    0.06
    Activations Density 0.012%

    No Known Activations