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. 77130
    Prev
    Next
    INDEX
    Explanations

    references to seasonal changes and natural phenomena

    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
     nackte
    -0.08
    eteria
    -0.07
     putas
    -0.06
    bern
    -0.06
     recall
    -0.06
    zk
    -0.06
     nominal
    -0.06
     rainy
    -0.06
    venience
    -0.06
    ög
    -0.06
    POSITIVE LOGITS
    æľĢä½³
    0.07
     viewing
    0.07
     week
    0.07
    ÙĦت
    0.07
    DMI
    0.06
    abella
    0.06
    fak
    0.06
    clared
    0.06
    ieber
    0.06
     optimal
    0.06
    Activations Density 0.001%

    No Known Activations