© 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. 130365
    Prev
    Next
    INDEX
    Explanations

    variations of the prefix "uro-" related to medical or biological 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
    nw
    -0.07
    p
    -0.07
    rar
    -0.06
    pire
    -0.06
    mach
    -0.06
    ugo
    -0.06
    pom
    -0.06
    rand
    -0.06
    rlen
    -0.06
    nova
    -0.06
    POSITIVE LOGITS
    duct
    0.08
    der
    0.08
    logy
    0.08
    ton
    0.08
    des
    0.07
    sp
    0.07
    scopic
    0.07
    ductory
    0.07
    shima
    0.07
    ly
    0.07
    Activations Density 0.087%

    No Known Activations