© 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. 95431
    Prev
    Next
    INDEX
    Explanations

    concepts of similarity and relationships between items or ideas

    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
    icken
    -0.08
    ura
    -0.08
    ilot
    -0.07
    Ñīин
    -0.07
    zia
    -0.07
    XH
    -0.07
    kami
    -0.07
    عات
    -0.07
    ilyn
    -0.07
    onda
    -0.06
    POSITIVE LOGITS
    æĻ´
    0.07
    аÑĤкÑĥ
    0.06
    ettle
    0.06
     Geo
    0.06
     Ve
    0.06
    CAPE
    0.06
    DeviceInfo
    0.06
    .priv
    0.06
    uppe
    0.05
    огÑĥ
    0.05
    Activations Density 0.037%

    No Known Activations