© 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. 31288
    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
    arkin
    -0.08
    elu
    -0.07
    ayah
    -0.07
    hta
    -0.07
    747
    -0.06
    adol
    -0.06
    adium
    -0.06
    olid
    -0.06
    sak
    -0.06
     neighborhood
    -0.06
    POSITIVE LOGITS
    -addon
    0.07
    .':
    0.07
    Evaluator
    0.07
    erman
    0.07
    몰
    0.06
     kancel
    0.06
    çĵ
    0.06
    maal
    0.06
    ÑģоÑĤ
    0.06
    iaux
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.