© 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. 15-LLAMASCOPE-RES-131K
    11. 90738
    Prev
    Next
    INDEX
    Explanations

    references to celebrity behavior and controversies

    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
    ouns
    -0.07
    Uvs
    -0.06
    à¹Ģà¸Ńà¸ģ
    -0.06
    ìķ½
    -0.06
    pora
    -0.06
    éĻµ
    -0.06
    .scalablytyped
    -0.06
    propri
    -0.06
    imports
    -0.06
    ainted
    -0.06
    POSITIVE LOGITS
     Pere
    0.07
    vac
    0.07
    fw
    0.06
    twig
    0.06
     disorder
    0.06
     reportedly
    0.06
    殿
    0.06
     court
    0.06
     Guid
    0.06
    dorf
    0.06
    Activations Density 0.007%

    No Known Activations