© 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 EvalsExportsinterp-engineNEWAPI 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. 81856
    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
    egra
    -0.06
    ovable
    -0.06
    beer
    -0.06
    Comple
    -0.06
    IFO
    -0.06
    ubu
    -0.06
     elementary
    -0.06
    å¤į
    -0.06
     ÙħØ´
    -0.06
     Hayward
    -0.06
    POSITIVE LOGITS
    esson
    0.07
    .scalablytyped
    0.07
     simult
    0.07
    ieee
    0.07
    анов
    0.07
    ://%
    0.07
    erable
    0.06
    mozilla
    0.06
    SupportedContent
    0.06
    PostalCodes
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.