© 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. 118658
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers likely representing telephone numbers

    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
    aversal
    -0.09
    hower
    -0.08
    ovice
    -0.07
    unning
    -0.07
    hek
    -0.07
    ffen
    -0.07
    EMON
    -0.07
     Moines
    -0.07
    iens
    -0.07
    åĩ¡
    -0.07
    POSITIVE LOGITS
    <?↵
    0.07
    ableObject
    0.06
     toll
    0.06
    ynamo
    0.06
     Kos
    0.06
     wing
    0.06
    .defineProperty
    0.06
    öz
    0.06
    apse
    0.06
     Greater
    0.06
    Activations Density 0.002%

    No Known Activations