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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 125562
    Prev
    Next
    INDEX
    Explanations

    descriptive language about performance and potential in a sports context

    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
     Pregn
    -0.07
    preg
    -0.07
     pregnant
    -0.07
    uw
    -0.07
    illon
    -0.07
     retired
    -0.07
    addock
    -0.07
    exus
    -0.06
    _reduce
    -0.06
     retire
    -0.06
    POSITIVE LOGITS
    -development
    0.06
    ÙĨÙħ
    0.06
     aforementioned
    0.06
     preco
    0.06
     underage
    0.06
    ypad
    0.06
     WOW
    0.06
    RITE
    0.06
     FixedUpdate
    0.06
    acons
    0.06
    Activations Density 0.006%

    No Known Activations