© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56970
    Prev
    Next
    INDEX
    Explanations

    technical terms related to design specifications and shapes

    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
     network
    -0.06
    abyrin
    -0.06
    cycle
    -0.06
     cycle
    -0.06
     sum
    -0.06
     arg
    -0.06
     rob
    -0.06
    cam
    -0.05
    ptest
    -0.05
     bare
    -0.05
    POSITIVE LOGITS
     shape
    0.19
     Shape
    0.17
    shape
    0.17
    Shape
    0.16
     shapes
    0.15
    _shape
    0.15
     shaped
    0.15
    shapes
    0.14
    -shaped
    0.14
     Shapes
    0.14
    Activations Density 0.138%

    No Known Activations