© 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. 29282
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and their properties

    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
    ichel
    -0.07
    òng
    -0.07
    _PHYS
    -0.07
    lfw
    -0.07
    uchi
    -0.06
    iola
    -0.06
     deepest
    -0.06
     Local
    -0.06
    Od
    -0.06
    ën
    -0.06
    POSITIVE LOGITS
     acute
    0.06
    ulers
    0.06
     ---------------------------------------------------------------------------↵
    0.06
    imits
    0.06
    bih
    0.06
     Propel
    0.06
     formation
    0.06
    arta
    0.06
     lent
    0.06
     Guerrero
    0.06
    Activations Density 0.010%

    No Known Activations