© 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. 15-LLAMASCOPE-RES-131K
    11. 87705
    Prev
    Next
    INDEX
    Explanations

    HTML closing tags

    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
    annt
    -0.07
    ente
    -0.07
    ospace
    -0.06
    umbed
    -0.06
    fal
    -0.06
    erland
    -0.06
     оÑĤп
    -0.06
    yo
    -0.06
    evice
    -0.06
    omp
    -0.06
    POSITIVE LOGITS
    OLE
    0.07
    ¤
    0.06
     WebClient
    0.06
    orno
    0.06
    405
    0.06
    æ¿Ł
    0.06
    VERRIDE
    0.06
    _customize
    0.06
    STYPE
    0.06
    ìļ±
    0.06
    Activations Density 0.007%

    No Known Activations