© 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. 16861
    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
     latest
    -0.07
    ugas
    -0.07
     extremism
    -0.06
    ificador
    -0.06
     мил
    -0.06
    _markers
    -0.06
     lately
    -0.06
     recent
    -0.06
    Ń
    -0.06
    976
    -0.06
    POSITIVE LOGITS
    MMdd
    0.10
    esor
    0.07
    ëĭī
    0.07
    ABCDEFGHIJKLMNOP
    0.07
    ahoma
    0.07
     tôi
    0.06
    achu
    0.06
    ecture
    0.06
     consect
    0.06
    ABCDEFGHI
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.