© 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. 95210
    Prev
    Next
    INDEX
    Explanations

    prepositions and words indicating relationships between entities

    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
    letcher
    -0.06
    jh
    -0.06
    osit
    -0.06
     Paren
    -0.06
    isu
    -0.06
    зÑĥ
    -0.06
     srd
    -0.06
    aho
    -0.06
    emoc
    -0.05
    (s
    -0.05
    POSITIVE LOGITS
    ÃŃÅ¡
    0.07
    /umd
    0.07
    ;element
    0.07
    ald
    0.07
    heimer
    0.07
    GAN
    0.06
    orden
    0.06
    hoff
    0.06
    edir
    0.06
    benh
    0.06
    Activations Density 0.038%

    No Known Activations