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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94273
    Prev
    Next
    INDEX
    Explanations

    references to musical activities 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
    çĽijåIJ¬é¡µéĿ¢
    -0.08
    izon
    -0.07
    IPPING
    -0.07
    _dual
    -0.07
     FLAC
    -0.07
     helicopt
    -0.06
    êm
    -0.06
    avr
    -0.06
     erotische
    -0.06
    dealloc
    -0.06
    POSITIVE LOGITS
     membership
    0.08
     members
    0.08
     member
    0.08
     memb
    0.07
     sheet
    0.07
     Membership
    0.06
     hal
    0.06
    members
    0.06
     Members
    0.06
     ple
    0.06
    Activations Density 0.006%

    No Known Activations