© 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 EvalsExportsinterp-engineNEWAPI 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. 79869
    Prev
    Next
    INDEX
    Explanations

    references to personal development and influential figures in that field

    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
    oplan
    -0.07
    izon
    -0.06
    à¥ĥद
    -0.06
    ände
    -0.06
     cogn
    -0.06
    ousel
    -0.06
    éĬ
    -0.06
    umar
    -0.06
    ovan
    -0.06
    iant
    -0.06
    POSITIVE LOGITS
    Clients
    0.08
     clients
    0.07
     Clients
    0.07
     Yoshi
    0.07
    .clients
    0.07
    _clients
    0.07
     Buccane
    0.07
     Gest
    0.07
    clients
    0.06
    beck
    0.06
    Activations Density 0.018%

    No Known Activations