© 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 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. 17-LLAMASCOPE-RES-131K
    11. 71216
    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
    ç¼
    -0.08
    antha
    -0.07
    ALLE
    -0.06
    orget
    -0.06
    ardin
    -0.06
    aci
    -0.06
    ihar
    -0.06
    815
    -0.06
    isin
    -0.06
    æĵ
    -0.06
    POSITIVE LOGITS
     ×
    0.07
     leh
    0.07
    immel
    0.07
    ×Ļ×
    0.06
     ש
    0.06
    ×ķ×
    0.06
    inalg
    0.06
    dere
    0.06
     Beaut
    0.06
     ׾
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.