© 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. 117017
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the degree of something, particularly relating to quantity or intensity

    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
     both
    -0.07
    isch
    -0.07
     somehow
    -0.07
    rp
    -0.06
    oret
    -0.06
    itto
    -0.06
    uala
    -0.06
    achel
    -0.06
    ories
    -0.06
     Mast
    -0.06
    POSITIVE LOGITS
     anymore
    0.11
     nor
    0.09
    zem
    0.08
    à¹ĥà¸Ķ
    0.07
     hã
    0.07
     Nor
    0.07
     nÃło
    0.07
    ä¹Łä¸į
    0.07
    LTE
    0.07
     EITHER
    0.06
    Activations Density 0.017%

    No Known Activations