© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127144
    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
    LBL
    -0.08
    ZERO
    -0.07
    ï¼IJ
    -0.06
    scal
    -0.06
     <<=
    -0.06
     White
    -0.06
    966
    -0.06
    534
    -0.06
    eturn
    -0.06
     Jug
    -0.06
    POSITIVE LOGITS
    obus
    0.07
    ebin
    0.07
    ullan
    0.07
     ëĺIJíķľ
    0.07
    ureau
    0.06
    ella
    0.06
    alat
    0.06
     derp
    0.06
    ÏĥηÏĤ
    0.06
     Blogs
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.