© 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. 38652
    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
    astle
    -0.07
     ει
    -0.07
    -Clause
    -0.07
    erp
    -0.07
    ÎŃλ
    -0.06
    'gc
    -0.06
    ersions
    -0.06
     wrought
    -0.06
     Vác
    -0.06
    edis
    -0.06
    POSITIVE LOGITS
     anch
    0.07
    ãĥ¼ãĥ³
    0.06
     Hier
    0.06
     occasional
    0.06
    ValuePair
    0.06
    yas
    0.06
     cap
    0.06
    oul
    0.06
     ot
    0.05
     vis
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.