© 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. 15-LLAMASCOPE-RES-131K
    11. 27273
    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
    âĢª
    -0.06
     å¾ĴæŃ©
    -0.06
    .Direction
    -0.06
    æĸ¹åIJij
    -0.06
    Sharper
    -0.06
    諾
    -0.06
     Maths
    -0.06
    AIL
    -0.05
     TERMIN
    -0.05
    sic
    -0.05
    POSITIVE LOGITS
    awan
    0.07
    vae
    0.07
     ones
    0.07
    render
    0.07
    ukkit
    0.07
    ॰
    0.06
    -spacing
    0.06
     uveden
    0.06
     sort
    0.06
     Lust
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.