© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 85425
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate reflection or evaluation of concepts

    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
    á»Ļng
    -0.08
    yla
    -0.07
    EMPLARY
    -0.07
    ÑĶм
    -0.07
    RG
    -0.07
    _ASCII
    -0.07
    æĨ
    -0.07
     moyen
    -0.07
    ắt
    -0.07
    ưỡng
    -0.07
    POSITIVE LOGITS
     reality
    0.09
     Ñģобой
    0.07
    oul
    0.07
     Reality
    0.07
    ieve
    0.07
     Baum
    0.07
     changes
    0.06
    itzer
    0.06
     accurately
    0.06
     realities
    0.06
    Activations Density 0.008%

    No Known Activations