© 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. 9-LLAMASCOPE-RES-131K
    11. 98554
    Prev
    Next
    INDEX
    Explanations

    phrases related to establishment and maintenance processes

    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
    antha
    -0.07
    AYS
    -0.06
    ÏĦÏħ
    -0.06
    740
    -0.06
    ays
    -0.06
    .bel
    -0.06
    XL
    -0.06
    293
    -0.06
    à¹Ħà¸Ķ
    -0.06
    QL
    -0.06
    POSITIVE LOGITS
     neod
    0.07
    UpInside
    0.07
    lier
    0.06
     VÅ¡ech
    0.06
    riad
    0.06
    duit
    0.06
    roma
    0.06
    ObjectContext
    0.06
    inator
    0.06
    Phones
    0.06
    Activations Density 0.002%

    No Known Activations