© 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 EvalsExportsinterp-engineNEWAPI 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. 72234
    Prev
    Next
    INDEX
    Explanations

    references to phone numbers and contact information

    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
    ousel
    -0.07
    ogan
    -0.07
     {?>↵
    -0.07
    ovit
    -0.07
    quette
    -0.07
    ngen
    -0.07
    anian
    -0.06
    µ¬
    -0.06
    iyat
    -0.06
    UGIN
    -0.06
    POSITIVE LOGITS
     telephone
    0.07
    suma
    0.06
    DisplayStyle
    0.06
     bif
    0.06
    iced
    0.06
     Ston
    0.06
    inez
    0.06
    ubs
    0.06
     Telephone
    0.06
     toggle
    0.06
    Activations Density 0.004%

    No Known Activations