© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4189
    Prev
    Next
    INDEX
    Explanations

    discourses surrounding social and political issues, particularly those involving community dynamics and systemic challenges

    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
    ÏĨÏħ
    -0.07
    atches
    -0.06
    Argb
    -0.06
    gabe
    -0.06
    STALL
    -0.06
    .Async
    -0.06
    lü
    -0.06
    ıt
    -0.06
    λλά
    -0.06
     kariy
    -0.06
    POSITIVE LOGITS
     focus
    0.10
    focus
    0.09
    Focus
    0.08
     focuses
    0.08
     Focus
    0.07
    å®ĺæĸ¹
    0.07
     Western
    0.07
    _focus
    0.07
     official
    0.07
     focused
    0.07
    Activations Density 0.044%

    No Known Activations