© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82503
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to academic degrees

    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
    urent
    -0.07
    à¹Ģà¸Ĥà¸ķ
    -0.07
    ivatel
    -0.06
    êm
    -0.06
    asant
    -0.06
    inem
    -0.06
    ounds
    -0.06
    880
    -0.06
    phies
    -0.06
    ãĥ«ãĥĪ
    -0.06
    POSITIVE LOGITS
    çľ¾
    0.07
    æĭ¬
    0.06
    elor
    0.06
    зано
    0.06
    atisch
    0.06
     cause
    0.06
     chor
    0.06
    ieri
    0.06
    _inches
    0.06
     Ped
    0.06
    Activations Density 0.020%

    No Known Activations