© 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. 88997
    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
    ogo
    -0.06
    .Annotations
    -0.06
    owitz
    -0.06
    iges
    -0.06
    ún
    -0.06
    igo
    -0.05
    ails
    -0.05
    agination
    -0.05
    INO
    -0.05
     ones
    -0.05
    POSITIVE LOGITS
    ilos
    0.08
    θÎŃ
    0.06
     metav
    0.06
    <boost
    0.06
     Modular
    0.06
    sy
    0.06
     >č↵
    0.06
    ayload
    0.06
     modular
    0.06
    sdk
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.