© 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. 4171
    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
    -NLS
    -0.06
    _AA
    -0.06
    incinn
    -0.06
    èĬ¸
    -0.06
    locals
    -0.05
    dül
    -0.05
    æĿī
    -0.05
    /disc
    -0.05
    æķ¬
    -0.05
     felt
    -0.05
    POSITIVE LOGITS
    abra
    0.08
    icode
    0.08
    ắc
    0.07
    aise
    0.07
    aidu
    0.07
    pty
    0.07
    EDA
    0.07
    kelas
    0.07
    ief
    0.07
    aised
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.