© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98300
    Prev
    Next
    INDEX
    Explanations

    references to physical attributes and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    857
    -0.07
    ma
    -0.06
    ienes
    -0.06
    eniable
    -0.06
    åŀ
    -0.06
     Vice
    -0.06
    otti
    -0.05
    lier
    -0.05
    shaw
    -0.05
    åķ
    -0.05
    POSITIVE LOGITS
    YRO
    0.08
    ortho
    0.08
    Å¡ti
    0.07
    ılıç
    0.07
    поÑĢ
    0.07
    andles
    0.07
    elpers
    0.07
    μÏĮ
    0.07
     ÄĮer
    0.06
    aval
    0.06
    Activations Density 0.037%

    No Known Activations