© 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. 76311
    Prev
    Next
    INDEX
    Explanations

    phrases related to the art scene and community engagement

    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
    uite
    -0.07
    èĬ¬
    -0.06
     Locker
    -0.06
     Lang
    -0.06
    -------------↵
    -0.06
    uyo
    -0.06
    :↵
    -0.06
    åĤĻ
    -0.06
     Leaf
    -0.06
    adden
    -0.05
    POSITIVE LOGITS
     local
    0.09
    local
    0.09
     LOCAL
    0.08
     locals
    0.08
    -local
    0.08
     Local
    0.08
     locally
    0.08
     lokal
    0.08
     city
    0.08
    Local
    0.07
    Activations Density 0.011%

    No Known Activations