© 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. 59238
    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
    endum
    -0.06
    iland
    -0.06
     Turk
    -0.06
    idan
    -0.06
    edition
    -0.06
    .pm
    -0.06
     gn
    -0.06
     somehow
    -0.05
     Mil
    -0.05
    ffi
    -0.05
    POSITIVE LOGITS
     Coalition
    0.08
    ToDevice
    0.08
    ãĥ©ãĤ¤ãĥĪ
    0.07
    วย
    0.07
    ëĿ¼ìĿ¸
    0.07
    @\
    0.07
    çħ¤
    0.07
    MUX
    0.06
     Pixels
    0.06
    lock
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.