© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77326
    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
    ziej
    -0.08
    æľĿ
    -0.07
    MO
    -0.07
    okit
    -0.07
    izzer
    -0.07
    öst
    -0.07
    üf
    -0.06
    istros
    -0.06
     AssemblyVersion
    -0.06
    abet
    -0.06
    POSITIVE LOGITS
    olia
    0.07
    ulan
    0.07
    addock
    0.06
    룬
    0.06
    comed
    0.06
    reso
    0.06
    ergency
    0.06
    hari
    0.06
    ARGV
    0.06
     Fif
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.