© 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. 76556
    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
    izu
    -0.07
    anik
    -0.07
     cÃŃt
    -0.07
     Nagar
    -0.07
     Smy
    -0.06
    esar
    -0.06
    TERS
    -0.06
    .Middle
    -0.06
    ENA
    -0.06
    IZES
    -0.06
    POSITIVE LOGITS
    .ng
    0.07
     Nigeria
    0.07
     security
    0.07
    áŀ¶
    0.06
    dialogs
    0.06
    hart
    0.06
     toll
    0.06
    lein
    0.06
    appa
    0.06
    -security
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.