© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82201
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "do" in various 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
    Ñīин
    -0.07
    leigh
    -0.07
    anta
    -0.07
    elon
    -0.07
    alle
    -0.06
    IntPtr
    -0.06
    §è¡Į
    -0.06
    elta
    -0.06
    ieber
    -0.06
    iston
    -0.06
    POSITIVE LOGITS
     bunu
    0.08
     this
    0.08
    è¿Ļ个
    0.08
     nÃły
    0.07
    Ú©Ùĩ
    0.07
     ذÙĦÙĥ
    0.07
     doing
    0.07
     Äijó
    0.07
    è¿Ļä¸Ģ
    0.07
    this
    0.07
    Activations Density 0.019%

    No Known Activations