© 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. 17-LLAMASCOPE-RES-131K
    11. 16978
    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
    istrovstvÃŃ
    -0.09
    utra
    -0.08
    @mail
    -0.07
    ANJI
    -0.07
    yb
    -0.07
    ollo
    -0.07
    VISIBLE
    -0.07
    amo
    -0.07
    AREST
    -0.06
    شد
    -0.06
    POSITIVE LOGITS
     Adler
    0.06
    elder
    0.06
    506
    0.06
    apa
    0.06
    ÑĢава
    0.06
    Ãĭ
    0.06
    -pill
    0.05
     odpowied
    0.05
    -wave
    0.05
     Sky
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.