© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 59742
    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
    illi
    -0.06
     selv
    -0.06
    ìłĦ
    -0.06
    alc
    -0.05
    ya
    -0.05
     replaced
    -0.05
     offshore
    -0.05
    ht
    -0.05
    hee
    -0.05
    heim
    -0.05
    POSITIVE LOGITS
    stage
    0.09
     stage
    0.08
    ãĥ³ãĥij
    0.07
     اÙĦÙĨÙĩ
    0.07
    elight
    0.07
    öyle
    0.07
    ož
    0.07
    orning
    0.07
    _STAGE
    0.07
     Stage
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.