© 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. 126714
    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
    à¤
    -0.07
     etc
    -0.07
    âĢĮشدÙĩ
    -0.06
    rels
    -0.06
    ibu
    -0.06
     scand
    -0.06
     Cutter
    -0.06
    baru
    -0.06
    —"
    -0.06
    ICS
    -0.06
    POSITIVE LOGITS
    igli
    0.07
    869
    0.06
    uiten
    0.06
    ãĥ³ãĤ°ãĥ«
    0.06
    igon
    0.06
     ì¶ľìŀ¥
    0.06
    yster
    0.06
    enheim
    0.06
     punt
    0.06
    itti
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.