© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 60268
    Prev
    Next
    INDEX
    Explanations

    the name "Joanne" and its variations

    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
    uner
    -0.07
    rous
    -0.07
    PropertyChanged
    -0.07
    anted
    -0.06
     Julien
    -0.06
    Concurrency
    -0.06
    lops
    -0.06
    icaret
    -0.06
    ymous
    -0.06
    ijkstra
    -0.06
    POSITIVE LOGITS
    anna
    0.08
    anne
    0.08
    elle
    0.07
    èī
    0.07
    annel
    0.07
    Ùģس
    0.07
    elow
    0.07
    eyh
    0.07
    ÌĪ
    0.07
    ève
    0.07
    Activations Density 0.008%

    No Known Activations