© 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. 128305
    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
    ighbor
    -0.09
    lero
    -0.09
    ehler
    -0.08
     saya
    -0.07
    rible
    -0.07
    paque
    -0.07
    luet
    -0.07
    ombine
    -0.07
    ίγ
    -0.07
    ancia
    -0.07
    POSITIVE LOGITS
    ius
    0.06
    akis
    0.05
     hadn
    0.05
    aster
    0.05
    zos
    0.05
    jos
    0.05
     AppModule
    0.05
     Debate
    0.05
    uren
    0.05
    浩
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.