© 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. 85694
    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
    -0.06
    ankan
    -0.06
    RFC
    -0.06
     ÑĤÑĥÑĤ
    -0.06
     fuss
    -0.06
    CEF
    -0.06
     Gerald
    -0.06
    ãĥªãĤ«
    -0.06
     Lowell
    -0.06
    nic
    -0.05
    POSITIVE LOGITS
    lluminate
    0.08
    ustralian
    0.07
    axon
    0.07
    ionic
    0.07
    iti
    0.07
    esian
    0.07
    uese
    0.06
    @student
    0.06
     ÙĬج
    0.06
    ropoda
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.