© 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. 129486
    Prev
    Next
    INDEX
    Explanations

    names of organizations and places related to religion and community

    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
     called
    -0.08
    rosso
    -0.07
     known
    -0.06
    unda
    -0.06
    adb
    -0.06
     ph
    -0.06
     close
    -0.06
    леÑĩ
    -0.06
       
    -0.06
     tw
    -0.06
    POSITIVE LOGITS
     instead
    0.07
     ÙĨسبة
    0.07
    uddle
    0.07
    instead
    0.07
     вмеÑģÑĤ
    0.07
     اختص
    0.07
    unitOfWork
    0.07
    posables
    0.06
     Barg
    0.06
    (er
    0.06
    Activations Density 0.034%

    No Known Activations