© 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. 40204
    Prev
    Next
    INDEX
    Explanations

    identifiers and descriptors related to events and awards

    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
     Hoy
    -0.07
     Caucas
    -0.06
    оÑĢдин
    -0.06
     Caucasian
    -0.06
    PropertyValue
    -0.06
    221
    -0.05
    obili
    -0.05
    866
    -0.05
    http
    -0.05
    osi
    -0.05
    POSITIVE LOGITS
    icipation
    0.08
    rippling
    0.07
    pike
    0.07
    çħ§
    0.07
    embre
    0.07
    933
    0.07
    ideshow
    0.07
     moci
    0.07
    /category
    0.07
     participation
    0.06
    Activations Density 0.001%

    No Known Activations