© 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. 16449
    Prev
    Next
    INDEX
    Explanations

    terms related to circularity and circular shapes

    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
    ptions
    -0.07
    tere
    -0.07
    ãĤ¼
    -0.07
    è²´
    -0.07
    chod
    -0.07
    ÑĢава
    -0.07
    áce
    -0.07
    AGEMENT
    -0.07
    'gc
    -0.07
    agers
    -0.07
    POSITIVE LOGITS
    s
    0.10
    ally
    0.07
    uits
    0.07
    gio
    0.07
    sut
    0.07
    iola
    0.07
     Circus
    0.07
    ilio
    0.07
    (circle
    0.06
     Circuit
    0.06
    Activations Density 0.005%

    No Known Activations