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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89926
    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
    ORMAT
    -0.07
    ãĥ³ãĥĨ
    -0.07
    |int
    -0.07
    RODUCTION
    -0.07
    |array
    -0.07
    jourd
    -0.07
    illis
    -0.07
    osemite
    -0.06
    ãĥ¼ãĥIJ
    -0.06
    еÑĢи
    -0.06
    POSITIVE LOGITS
    allen
    0.06
    tere
    0.06
     Um
    0.06
     kole
    0.05
     needed
    0.05
     totals
    0.05
    nit
    0.05
    Äį
    0.05
     (*)
    0.05
     factor
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.