© 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. 28566
    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
    INET
    -0.07
    åĩºåĵģèĢħ
    -0.07
    layan
    -0.06
    æ£ļ
    -0.06
    .toObject
    -0.06
     возÑĢаÑģÑĤа
    -0.06
    ë³´ì¦Ŀê¸Ī
    -0.06
    eling
    -0.06
     Friend
    -0.06
     satisf
    -0.06
    POSITIVE LOGITS
    cker
    0.07
     mitt
    0.06
    eric
    0.06
    igli
    0.06
    104
    0.06
     our
    0.06
    settings
    0.06
    wal
    0.06
     наÑĪей
    0.06
    axy
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.