© 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. 78501
    Prev
    Next
    INDEX
    Explanations

    references to significant communication events involving the Pope and interreligious dialogue

    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
    znam
    -0.08
    .createClass
    -0.07
    ubu
    -0.07
    %C
    -0.07
    ucha
    -0.07
    rowse
    -0.07
    .FindGameObjectWithTag
    -0.07
     vá»ĭ
    -0.07
     nonzero
    -0.07
    chwitz
    -0.07
    POSITIVE LOGITS
     «
    0.07
     diff
    0.06
    interp
    0.06
    nnen
    0.06
    ű
    0.06
    hev
    0.06
    pty
    0.06
     reprodu
    0.06
    ktor
    0.06
     Olsen
    0.06
    Activations Density 0.001%

    No Known Activations