© 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. 9-LLAMASCOPE-RES-131K
    11. 95749
    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
     ï
    -0.06
     cr
    -0.06
     pal
    -0.06
     regimes
    -0.06
     grit
    -0.05
     mass
    -0.05
    /Set
    -0.05
    prises
    -0.05
     toler
    -0.05
     CG
    -0.05
    POSITIVE LOGITS
    ẫ
    0.09
    contri
    0.08
    ież
    0.07
    UTO
    0.07
    ingleton
    0.07
    jeme
    0.07
    attles
    0.07
    habi
    0.07
    大åħ¨
    0.07
    lider
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.