© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 85006
    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
    apel
    -0.07
     Expedition
    -0.06
    aceous
    -0.06
    اØ
    -0.06
    lander
    -0.06
    umbo
    -0.06
    _xs
    -0.05
     outs
    -0.05
     nast
    -0.05
     Feature
    -0.05
    POSITIVE LOGITS
    ospace
    0.08
    ags
    0.07
     Kraft
    0.07
    adolu
    0.07
    volume
    0.07
    ogn
    0.07
    /gin
    0.07
    aidu
    0.06
    ftype
    0.06
    StackNavigator
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.