© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 105926
    Prev
    Next
    INDEX
    Explanations

    terms and references related to general practitioners (GPs) and their practices

    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
    ray
    -0.07
    iek
    -0.07
    kla
    -0.06
    ed
    -0.06
    ences
    -0.06
    otto
    -0.06
    gaard
    -0.06
    ìļķ
    -0.06
     ìľłíĺķ
    -0.06
    entity
    -0.06
    POSITIVE LOGITS
    ckett
    0.07
    اÙħÙĩ
    0.07
    iland
    0.07
    ëĵľë¡ľ
    0.07
    ruba
    0.06
    preneur
    0.06
    ίνα
    0.06
    innen
    0.06
    IDO
    0.06
     subscribing
    0.06
    Activations Density 0.005%

    No Known Activations