© 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. 128115
    Prev
    Next
    INDEX
    Explanations

    the word "much" and its synonyms in varying contexts

    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
    ãĢĤãĢĤ↵↵
    -0.07
    nám
    -0.07
    pline
    -0.07
     crossorigin
    -0.06
    isans
    -0.06
    reo
    -0.06
    دÙĬد
    -0.06
    ุà¸Ķ
    -0.06
     sola
    -0.06
     svens
    -0.06
    POSITIVE LOGITS
     which
    0.08
    icularly
    0.07
    cluding
    0.07
     especially
    0.07
    glob
    0.06
     коÑĤоÑĢого
    0.06
    ensis
    0.06
    ajÄħc
    0.06
    pecially
    0.06
     коÑĤоÑĢой
    0.06
    Activations Density 0.037%

    No Known Activations