© 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. 119758
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ickerView
    -0.07
    REFER
    -0.07
    æį·
    -0.07
     Cumhur
    -0.07
    åŀ
    -0.06
    quirrel
    -0.06
    à¹Ģว
    -0.06
    ersonic
    -0.06
    Ģ
    -0.06
    ÐļÐIJ
    -0.06
    POSITIVE LOGITS
    åIJ«
    0.07
    idding
    0.07
     Prev
    0.06
    jin
    0.06
    arde
    0.06
     reversal
    0.06
    RK
    0.06
     surrounded
    0.06
    ibar
    0.05
    .kernel
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.