Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95786
    Prev
    Next
    INDEX
    Explanations

    numerical references associated with a sequence or process

    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
    unma
    -0.07
    phem
    -0.07
    oman
    -0.07
     Gund
    -0.07
    kili
    -0.07
    øre
    -0.06
    stoff
    -0.06
     vir
    -0.06
    ascal
    -0.06
     Rosenstein
    -0.06
    POSITIVE LOGITS
    éŀ
    0.07
     Smile
    0.07
    &action
    0.06
    estone
    0.06
    >Main
    0.06
    ãģ«åĩº
    0.06
     AdapterView
    0.06
    828
    0.06
     destinationViewController
    0.06
    thal
    0.06
    Activations Density 0.004%

    No Known Activations