© 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. 83015
    Prev
    Next
    INDEX
    Explanations

    details about museums and their directors

    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
    ollen
    -0.06
    129
    -0.06
     Factory
    -0.06
    ÙħÙĬ
    -0.06
     Representation
    -0.05
     CRC
    -0.05
    uta
    -0.05
     representation
    -0.05
    etsk
    -0.05
    æĭľ
    -0.05
    POSITIVE LOGITS
     owners
    0.09
     owner
    0.09
    -owner
    0.08
    owner
    0.08
     proprietor
    0.08
    itone
    0.08
    -caret
    0.07
    (owner
    0.07
    _owner
    0.07
    gings
    0.07
    Activations Density 0.042%

    No Known Activations