© 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 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. 17-LLAMASCOPE-RES-131K
    11. 3583
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "of" in various contexts

    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
    ioned
    -0.07
    ÑģÑĮ
    -0.06
    fully
    -0.06
    able
    -0.06
    ingers
    -0.06
    aged
    -0.06
    avor
    -0.06
    awy
    -0.06
    INGER
    -0.06
    apat
    -0.06
    POSITIVE LOGITS
    chied
    0.07
    operation
    0.07
    æ¿ĥ
    0.07
     action
    0.07
     operation
    0.07
     дÑĸÑĹ
    0.07
    Enumerable
    0.07
    à¸ģำ
    0.07
    etz
    0.06
    chalk
    0.06
    Activations Density 0.109%

    No Known Activations