© 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. 82766
    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
     Deng
    -0.06
    ónico
    -0.06
     Reasons
    -0.06
    blr
    -0.05
     alongside
    -0.05
    è¿
    -0.05
    /r
    -0.05
     Basically
    -0.05
     smaller
    -0.05
     BaseController
    -0.05
    POSITIVE LOGITS
    ivar
    0.07
    folio
    0.07
    oci
    0.07
     Fol
    0.07
    azu
    0.07
    565
    0.07
    again
    0.07
    eba
    0.07
    egie
    0.07
    util
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.