© 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. 75145
    Prev
    Next
    INDEX
    Explanations

    terms related to secrecy and well-known facts

    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
     اÙĦرÙħزÙĬØ©
    -0.07
    oga
    -0.07
    olid
    -0.07
    رش
    -0.07
    uide
    -0.06
    мовÑĸÑĢ
    -0.06
    ole
    -0.06
    oret
    -0.06
    ermen
    -0.06
    олоÑģ
    -0.06
    POSITIVE LOGITS
     bahwa
    0.08
     rằng
    0.07
    oron
    0.07
    221
    0.06
    96
    0.06
     among
    0.06
     that
    0.06
    AMP
    0.06
    601
    0.06
    _firestore
    0.06
    Activations Density 0.001%

    No Known Activations