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

    Neuronpedia

    Jacobian LensNEW
    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. 87473
    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
    ÙĪÙĬÙĥ
    -0.07
    çľł
    -0.07
    ุà¸į
    -0.07
    294
    -0.06
    âĶĶ
    -0.06
    StackNavigator
    -0.06
    ickers
    -0.06
    еÐ
    -0.06
    969
    -0.06
    .crm
    -0.06
    POSITIVE LOGITS
    SizeMode
    0.06
    nite
    0.06
    insky
    0.06
    ìĭ¤
    0.06
     Obama
    0.06
     Rah
    0.06
    []
    0.06
    ccording
    0.06
     Dise
    0.06
    BoundingBox
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.