© 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. 121047
    Prev
    Next
    INDEX
    Explanations

    words and phrases that imply close relationships and connections between people

    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
    778
    -0.07
    meric
    -0.06
    еÑĢг
    -0.06
    lew
    -0.06
    immel
    -0.06
    ilda
    -0.06
    avo
    -0.06
    iteral
    -0.06
    ü
    -0.06
    mond
    -0.06
    POSITIVE LOGITS
    aisy
    0.06
     togg
    0.06
     ÑıÑĢ
    0.06
    omy
    0.06
    ıf
    0.06
    anken
    0.06
    :::::
    0.06
     recap
    0.06
    rawn
    0.06
    æħİ
    0.06
    Activations Density 0.001%

    No Known Activations