© 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. 39018
    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
    angu
    -0.06
     riff
    -0.06
     re
    -0.06
     work
    -0.06
     &
    -0.06
     +
    -0.06
     mount
    -0.06
    ï¼Įä¸įè¿ĩ
    -0.05
     candid
    -0.05
    ota
    -0.05
    POSITIVE LOGITS
    iqueta
    0.08
    deme
    0.08
    ammo
    0.08
     UIStoryboard
    0.07
    æµħ
    0.07
    .observable
    0.07
    kol
    0.07
    amine
    0.07
    inati
    0.07
    æĶ¿
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.