© 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. 29306
    Prev
    Next
    INDEX
    Explanations

    instances of relational phrases regarding environments and locations

    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
    SimpleName
    -0.07
     toile
    -0.06
    аÑĢод
    -0.06
    aleb
    -0.06
    oref
    -0.06
    <>
    -0.06
    adel
    -0.06
    bakan
    -0.05
    ár
    -0.05
    areth
    -0.05
    POSITIVE LOGITS
     commercial
    0.09
     public
    0.09
     office
    0.08
    plode
    0.08
    .biz
    0.08
    åħ¬åħ±
    0.08
     business
    0.07
     professional
    0.07
    commercial
    0.07
     abroad
    0.07
    Activations Density 0.024%

    No Known Activations