© 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. 81886
    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
    ENTA
    -0.07
    ên
    -0.07
    ALER
    -0.06
    ÑģÑĮ
    -0.06
    assi
    -0.06
    essel
    -0.06
    Tracks
    -0.06
    .tele
    -0.06
     backwards
    -0.06
    tracks
    -0.06
    POSITIVE LOGITS
    lass
    0.07
    GroupId
    0.07
    磨
    0.06
     finale
    0.06
    escort
    0.06
    ä¸Ģ人
    0.06
    lasses
    0.06
    imeline
    0.06
    λά
    0.06
    074
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.