© 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. 9-LLAMASCOPE-RES-131K
    11. 95395
    Prev
    Next
    INDEX
    Explanations

    names and titles related to creative professionals or artistic endeavors

    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
    illac
    -0.09
    804
    -0.07
    zano
    -0.07
    illas
    -0.07
    isory
    -0.07
    olley
    -0.06
     Hust
    -0.06
    bull
    -0.06
    ITO
    -0.06
    iron
    -0.06
    POSITIVE LOGITS
     Pioneer
    0.07
    Votre
    0.07
    Į¨
    0.07
    strcasecmp
    0.06
    ANGUAGE
    0.06
    eft
    0.06
    .structure
    0.06
     Hra
    0.06
     Emblem
    0.06
    cdb
    0.06
    Activations Density 0.000%

    No Known Activations