© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 104231
    Prev
    Next
    INDEX
    Explanations

    terms related to telecommunications and user contact management

    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
    ç
    -0.07
    èĦ±
    -0.07
    HeaderCode
    -0.07
    alars
    -0.07
    /sites
    -0.07
    Portal
    -0.07
    ãĥ¼ãĤº
    -0.07
    CodeAt
    -0.07
    :frame
    -0.07
    _qs
    -0.07
    POSITIVE LOGITS
     contact
    0.09
     contacts
    0.08
     Contacts
    0.08
    contacts
    0.07
    contact
    0.07
    /contact
    0.07
     Contact
    0.06
    _contacts
    0.06
    Contacts
    0.06
     mass
    0.06
    Activations Density 0.026%

    No Known Activations