© 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. 15-LLAMASCOPE-RES-131K
    11. 61616
    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
    ereotype
    -0.07
    onya
    -0.07
    ediator
    -0.07
    elere
    -0.07
    sie
    -0.06
    evil
    -0.06
     Ske
    -0.06
    tas
    -0.06
    óÅĤ
    -0.06
    uts
    -0.06
    POSITIVE LOGITS
     âĸĪâĸĪâĸĪâĸĪâĸĪ
    0.07
     fucks
    0.07
    GGLE
    0.07
     Fuck
    0.07
     fucking
    0.06
     ÑģпÑĢавж
    0.06
     fucked
    0.06
    Ïģθ
    0.06
    afort
    0.06
    ácil
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.