© 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. 75255
    Prev
    Next
    INDEX
    Explanations

    references to people, especially in a professional or academic context

    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
    #__
    -0.10
    Äįel
    -0.09
    PÅĻÃŃ
    -0.09
    ãģĵãģ¡ãĤī
    -0.08
    midi
    -0.08
    dain
    -0.08
    _OBJC
    -0.08
    اعÙĬØ©
    -0.08
    ://%
    -0.08
    MZ
    -0.08
    POSITIVE LOGITS
    âĢ¦↵
    0.07
    âĢ¦
    0.06
     Omega
    0.06
     Consumers
    0.06
     merch
    0.05
    âĢ¦I
    0.05
     moder
    0.05
    âĢ¦"
    0.05
     âĢ¦
    0.05
    âĢ¦”
    0.05
    Activations Density 0.011%

    No Known Activations