© 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. 62388
    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
     Wenger
    -0.08
     Duc
    -0.07
     Flat
    -0.07
    illac
    -0.06
     semi
    -0.06
     flat
    -0.06
    attro
    -0.06
    ÄĻk
    -0.06
    iros
    -0.06
    _CFG
    -0.06
    POSITIVE LOGITS
    argon
    0.06
     forth
    0.06
    bie
    0.06
    anford
    0.06
    ìĦŃ
    0.06
     refunds
    0.06
    chwitz
    0.06
    ikip
    0.06
    endment
    0.06
     transitional
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.