© 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. 15-LLAMASCOPE-RES-131K
    11. 27605
    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
    entar
    -0.06
    .tar
    -0.06
     Film
    -0.06
    xca
    -0.06
     Ka
    -0.06
    unker
    -0.05
    ë²Ħ
    -0.05
     åįĬ
    -0.05
    rell
    -0.05
    λλη
    -0.05
    POSITIVE LOGITS
    ilir
    0.08
    ings
    0.07
     RedirectTo
    0.07
    IEW
    0.07
    RIX
    0.07
    aine
    0.07
     fitte
    0.07
    ENCIL
    0.07
     liberty
    0.06
    lds
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.