© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106363
    Prev
    Next
    INDEX
    Explanations

    patterns of numeric data or statistics related to sports events

    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
    евид
    -0.07
    ÑĦоÑĢ
    -0.07
    ewise
    -0.06
     uncont
    -0.06
    ogan
    -0.06
    amp
    -0.06
    piler
    -0.06
    .readValue
    -0.06
    uml
    -0.06
    ckill
    -0.06
    POSITIVE LOGITS
    vik
    0.07
    XmlNode
    0.06
    adiens
    0.06
    çIJ´
    0.06
    δή
    0.06
    мага
    0.06
     Sus
    0.06
    adir
    0.06
     pa
    0.06
    addtogroup
    0.06
    Activations Density 0.003%

    No Known Activations