© 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. 58686
    Prev
    Next
    INDEX
    Explanations

    references to the name "Rosalynn" or variations of it

    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
    utzer
    -0.06
    ister
    -0.06
    957
    -0.06
    uby
    -0.06
    umas
    -0.06
    Qualifier
    -0.06
     prescribed
    -0.06
     consort
    -0.06
    eren
    -0.06
    ighton
    -0.06
    POSITIVE LOGITS
    velt
    0.09
    /ros
    0.08
    mary
    0.08
    æŀĿ
    0.07
    adle
    0.07
    ocu
    0.07
    opolitan
    0.07
    оÑĢо
    0.07
    grese
    0.07
    çĭ
    0.06
    Activations Density 0.012%

    No Known Activations