© 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. 5414
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical combinations or aggregations

    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
    utow
    -0.08
    .FontStyle
    -0.07
    Æ°á»Ŀng
    -0.07
    iban
    -0.07
    agar
    -0.07
    ORS
    -0.07
    ihan
    -0.07
    kees
    -0.07
    FFE
    -0.07
    каÑģ
    -0.07
    POSITIVE LOGITS
     between
    0.12
     of
    0.09
     combination
    0.08
     several
    0.08
     two
    0.08
    combination
    0.08
     zwischen
    0.08
     giữa
    0.07
     multiple
    0.07
     Between
    0.07
    Activations Density 0.030%

    No Known Activations