© 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. 85574
    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
     [
    -0.06
    asm
    -0.06
     Reform
    -0.06
    iaux
    -0.06
     new
    -0.06
    ogen
    -0.06
     circular
    -0.06
     ,
    -0.05
    iel
    -0.05
     M
    -0.05
    POSITIVE LOGITS
    braco
    0.09
    ModelProperty
    0.09
    /apis
    0.08
    (=)
    0.08
     rowspan
    0.08
    leftright
    0.08
    thal
    0.08
    ĶåĽŀ
    0.08
    ëĿ¼ìĿ¸
    0.07
     Demp
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.