© 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. 88415
    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
    enville
    -0.07
     Allan
    -0.06
    [DllImport
    -0.06
     GObject
    -0.06
    ichert
    -0.06
    ptron
    -0.06
    (equalTo
    -0.06
    logen
    -0.06
     neither
    -0.06
    isman
    -0.06
    POSITIVE LOGITS
    ãĤ¤ãĥ³ãĥĪ
    0.07
     åĨ
    0.06
     Via
    0.06
    rai
    0.06
    viron
    0.06
    Ñĥг
    0.06
    /Area
    0.06
    wan
    0.06
     thing
    0.06
    otr
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.