© 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. 14653
    Prev
    Next
    INDEX
    Explanations

    terms related to telecommunications and communication technologies

    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
     gazet
    -0.07
     -
    -0.06
    zas
    -0.06
     everywhere
    -0.06
    ZA
    -0.06
     Tart
    -0.06
    663
    -0.06
     everybody
    -0.06
    ENS
    -0.06
     solvent
    -0.06
    POSITIVE LOGITS
    oodle
    0.07
    utin
    0.07
    BILE
    0.06
    iá»ģm
    0.06
    oÄŁ
    0.06
    oogle
    0.06
     åĦ
    0.06
    anooga
    0.06
    оÑı
    0.06
    .degree
    0.06
    Activations Density 0.163%

    No Known Activations