© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28817
    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
     â
    -0.09
     withd
    -0.08
     Türkçe
    -0.07
     Ãİ
    -0.07
     &#
    -0.07
    "^
    -0.07
    ÐĨн
    -0.07
     yans
    -0.07
     ÃĶ
    -0.07
    affer
    -0.07
    POSITIVE LOGITS
    0.11
    uti
    0.07
    âĢħ
    0.07
    .scalablytyped
    0.06
    ÌĨ
    0.06
    719
    0.06
    822
    0.06
    ®
    0.06
    irt
    0.06
    iloc
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.