© 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. 91925
    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
    åĪĩ
    -0.06
    INUX
    -0.06
     agency
    -0.05
     лÑİ
    -0.05
     decomposition
    -0.05
    695
    -0.05
    898
    -0.05
     اØ
    -0.05
    USIC
    -0.05
    011
    -0.05
    POSITIVE LOGITS
     shark
    0.07
    boot
    0.07
    eworld
    0.07
    temperature
    0.07
     franch
    0.07
    andler
    0.07
    amat
    0.07
    snake
    0.07
    enburg
    0.07
     Royals
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.