© 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. 87442
    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
    izza
    -0.07
    aida
    -0.06
    abay
    -0.06
    ì¹Ń
    -0.06
    ereo
    -0.06
    olum
    -0.06
    asl
    -0.06
    GORITH
    -0.06
    غ
    -0.06
    جا
    -0.06
    POSITIVE LOGITS
    erosis
    0.08
    Attempting
    0.07
    .scalablytyped
    0.07
    .Begin
    0.06
    auer
    0.06
    \Dependency
    0.06
    alous
    0.06
     DependencyProperty
    0.06
    _trap
    0.06
    nÃŃk
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.