© 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. 29147
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic or cultural settings

    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
    enza
    -0.07
    raq
    -0.07
    _ABI
    -0.07
    avicon
    -0.07
    baugh
    -0.07
    enze
    -0.07
    ekl
    -0.07
    ceae
    -0.07
    ichick
    -0.07
    emmel
    -0.07
    POSITIVE LOGITS
     dialect
    0.07
     spoken
    0.07
    екаÑĢ
    0.07
    ç³»
    0.06
    spoken
    0.06
     dial
    0.06
     vendors
    0.06
    ãģĿ
    0.06
     perv
    0.06
     Tes
    0.06
    Activations Density 0.001%

    No Known Activations