© 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 EvalsExportsinterp-engineNEWAPI 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. 15023
    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
    WithDuration
    -0.06
    macros
    -0.06
    NewLabel
    -0.06
     discrimin
    -0.06
     ultr
    -0.06
     macros
    -0.06
     tonight
    -0.06
    .construct
    -0.06
    rah
    -0.06
    ibus
    -0.06
    POSITIVE LOGITS
    Neg
    0.07
    оÑģÑĤÑĮ
    0.07
    phia
    0.07
    åłĤ
    0.07
    incerely
    0.07
    าà¸ķร
    0.07
    oyer
    0.06
    éric
    0.06
    ologies
    0.06
    Viewer
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.