© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106808
    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
    atchet
    -0.08
    ocket
    -0.07
    leck
    -0.07
    AGMA
    -0.07
     equ
    -0.07
    ανδ
    -0.07
    istribute
    -0.07
    ellig
    -0.06
    ulin
    -0.06
    ÙĪÙģ
    -0.06
    POSITIVE LOGITS
     testcase
    0.07
    orz
    0.06
     Clifford
    0.06
    aro
    0.06
    ium
    0.06
     embar
    0.06
     Cassidy
    0.06
     PM
    0.06
     PR
    0.06
     assist
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.