© 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. 71817
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-awareness and introspection

    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
    rais
    -0.08
    .Dependency
    -0.07
    ugi
    -0.07
    leri
    -0.07
    amp
    -0.07
    ventus
    -0.07
    .mob
    -0.07
    ÑĨин
    -0.07
    CELER
    -0.06
    Äĥ
    -0.06
    POSITIVE LOGITS
    usted
    0.07
    orro
    0.07
    xCB
    0.06
    endez
    0.05
    enger
    0.05
    ainer
    0.05
    ãģĹãģı
    0.05
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.05
     somehow
    0.05
    öh
    0.05
    Activations Density 0.027%

    No Known Activations