© 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. 15-LLAMASCOPE-RES-131K
    11. 61548
    Prev
    Next
    INDEX
    Explanations

    the expression of opinions and feelings about authority and social norms

    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
    дина
    -0.06
    utomation
    -0.06
    {:
    -0.06
     options
    -0.06
     mon
    -0.05
     Q
    -0.05
     prem
    -0.05
     double
    -0.05
     en
    -0.05
     dual
    -0.05
    POSITIVE LOGITS
    kus
    0.08
    uze
    0.08
     Sabha
    0.07
    ussen
    0.07
    UZ
    0.07
    uvo
    0.07
     hoop
    0.07
    ianne
    0.07
    æ°ı
    0.06
     anymore
    0.06
    Activations Density 0.019%

    No Known Activations